Language Model Decoding

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 108

Oct 5, 2026cs.RO

SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents

Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifiers but incur the latency of token-by-token generation. Recent shared-prefix methods reduce this cost by reusing encoded context and scoring multiple decisions in parallel, but do not model decision dependencies or verify execution. We propose SharedKV-BT, where each active node of a behavior tree (BT) exposes stage-local fields and candidates, and Shared-KV scores the candidates in parallel and passes the selected decision to a separate execution system. We tested SharedKV-BT on robot manipulation, mobile navigation, and computer-use tasks. Across three tasks, SharedKV-BT made typed decisions 2.36-4.15 times faster than prompt-matched autoregressive decoding. On the manipulation task, node-local Shared-KV improved joint decision accuracy from 75% to 94% and closed-loop success from 0% to 60%. Fixed-score policy replay showed that stage gating prevented out-of-order actions and external postconditions prevented premature completion.

Naoki Wake, Justin Wagle

Microsoft

Language Model Decoding Robot Task Planning Behavior Trees

Oct 5, 2026cs.CL

Can Language Models Learn to Reject Their Own Bad Reasoning Steps?

Verifier-guided decoding can prevent harmful reasoning steps from contaminating subsequent generation, but typically relies on an external learned verifier. We ask whether a language model can instead reject its own bad reasoning steps. We define a prefix's recoverability as the probability that the frozen generator can complete it correctly. Diagnostics show that adjacent recoverability changes are often difficult to resolve with practical Monte Carlo budgets, while same-prefix candidates exhibit a sparse low-recoverability tail. We introduce Self-Step Rejection (SSR), which trains a lightweight LoRA acceptance gate on the generator backbone while keeping the base model frozen. SSR uses confidence-qualified first-passage supervision: steps before the first resolved crossing of a root-relative recoverability barrier are accepted, the crossing step is rejected, and unresolved steps and suffixes are excluded. Training combines pointwise classification, same-prefix pairwise learning, and group-relative policy refinement using final-answer correctness. At inference, SSR accepts candidates or resamples from the unchanged prefix under rejection budgets, without an external learned verifier. Across three reasoning models and five mathematical reasoning benchmarks, SSR improves macro-average accuracy over single-pass decoding by 5.4--10.1 points using 1.21--1.40x as many generated tokens, and achieves the highest macro-average accuracy among evaluated step-level methods. Full-solution scaling methods require 4.47--8.27x the single-pass token cost for comparable performance.

Siheng Xiong, Xiaoze Liu, Yiqiao Jin +2

Georgia Institute of Technology · Purdue University

LLM Self-Correction Language Model Decoding Efficient Language Model Reasoning LLM Reasoning Reasoning Verification

Oct 5, 2026cs.AI

Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation

Text revision has become an integral component of large language models. This paper formulates revision such that it admits a Nash equilibrium: Token positions are players, vocabulary items are actions, and each player's utility is the language model's log conditional probability. We motivate the revision by showing that Nash equilibria can have exponentially higher likelihood than autoregressive outputs as the sequence length grows. We further propose Nash decoding, an algorithm that reaches an

\varepsilon

-Nash equilibrium in

O(1/\varepsilon)

time given access to the joint probability of tokens conditioned on a prompt. In practice, we run Nash decoding using conditional probability estimates from large language models and evaluate the resulting equilibria on question-answering benchmarks. On CLAPNQ, PubMedQA, and CoQA, Nash equilibria obtained from masked language models achieve higher F1 and ROUGE scores than autoregressive models up to

18\times

larger, without any fine-tuning or retraining, at the cost of additional test-time computation.

Alireza Jafari, Arman Adibi, Mohammad Ghavamzadeh +1

Department of Computer Science University of Virginia Charlottesville, VA, USA · School of Computer and Cyber Sciences Augusta University Augusta, GA, USA · Qualcomm AI Research San Diego, CA, USA

Nash Equilibrium Non-Autoregressive Text Generation Language Model Decoding

Oct 1, 2026cs.LG

Decoding Looped Transformers Better for (Almost) Free

Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each loop yields an intermediate representation decodable for the same next token, yet standard decoding discards earlier states. Because earlier loops embody less computation, recurrence inherently supplies aligned weak-and-strong prediction pairs without auxiliary models or external training. We introduce LoopCD, a training-free contrastive decoding framework that guides token selection by contrasting the final prediction with an earlier recurrent pass, operating either in logit space with one extra output pass (LoopCD-Logits) or in hidden-state space with zero output overhead (LoopCD-Hidden). Across four looped Transformer families, LoopCD delivers substantial, consistent gains at full recurrent depth: LoopCD-Logits raises Ouro-2.6B-Thinking's AIME 2024 pass@1 from 61.88% to 73.33%, while LoopCD-Hidden lifts Huginn's HumanEval pass@1 from 22.56% to 31.71%. Crucially, these performance gains enable halving the number of recurrent loops while still matching or exceeding full-depth unguided baselines, reducing forward FLOPs by 22.5% to 48.2%. By transforming intermediate recurrent states into effective guidance signals, LoopCD achieves superior decoding quality while substantially reducing inference compute.

Weihao Liu, Huangjie Zheng, Tianrong Chen +5

Apple

Efficient Transformer Inference Language Model Decoding Recurrent Transformers Contrastive Decoding

Oct 1, 2026cs.AI

Gacha Decoding: Eliciting Diverse Generations Through Instruction Following

We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-ended domains (in-the-wild chat, creative writing, planning for image generation, and protein design), Gacha Decoding significantly outperforms existing generation diversity approaches at equal quality (up to 2.4x Vendi over the next-best prior approach), reaching the same number of high-quality modes with over an order of magnitude fewer samples (11.0x) and discovering novel modes that no other approach surfaces. Our key insight is to treat diversity as an instruction-following problem: rather than relying on the LM's token entropy, we combine its instruction-following capability with randomness from an external RNG tool to scalably identify and realize distinct modes of the response space. This approach of "planning with dice" enables Gacha to invert the long-observed tension between diversity and model capability. As the underlying LM becomes a better instruction follower, diversity under Gacha Decoding consistently improves--even as its token entropy and diversity under prior approaches decline. Together, our results highlight that instruction following, rather than token entropy alone, can drive generation diversity.

Scott Geng, Yufei Zhang, Joseph Lee +3

University of Washington · Meta Superintelligence Labs

Language Model Decoding Diverse Text Generation

Sep 29, 2026cs.SD

AS $^2$ D: Accelerating On-Demand Audio Understanding on Mobile Devices

Speculative decoding accelerates autoregressive generation by using a smaller drafter to propose tokens for batched verification by a larger target. However, conventional speculative decoding couples drafting to the target's evolving verified prefix, serializing drafting and verification. We ask whether this dependency is necessary for source-conditioned generation. Our key observation is that, for audio language models, the input audio and user request can provide useful speculative candidates without following the target's evolving text prefix. We propose AS

^2

D (Audio Speculative Speculative Decoding), which enables target-decoupled drafting: an audio-conditioned drafter follows its own generation history while the target independently verifies and corrects ready candidates. Without usable candidates, the target advances alone. Thus, target feedback determines which candidates are committed but no longer determines when the drafter can make progress, enabling drafting and verification to proceed concurrently while retaining target-side verification and correction. We implement AS

^2

D in MNN for Android and evaluate two target models across four phones, seven datasets, and three tasks covering 12.2 hours of audio. Across four phones, AS

^2

D improves pooled ASR throughput by 42-76% over target-only decoding, while only 5.7% of evaluation windows are slower than target-only, compared with 58.1-63.0% for speculative baselines. For ASR, AS

^2

D reaches 97.33-98.20% of a hindsight per-window oracle's pooled throughput over the evaluated drafter/budget catalog. Native on-demand execution with a 7B target achieves up to 78% higher throughput than target-only. These results show that source-conditioned audio generation can relax the conventional dependence of speculative drafting on the target's evolving output prefix, exposing substantial parallelism for efficient inference.

Yunzhe Li, Kyoungjun Park, Hongzi Zhu +1

The University of Texas at Austin · Shanghai Jiao Tong University

On-Device Language Model Inference Language Model Decoding Speculative Decoding Audio-Language Models Automatic Speech Recognition

Sep 28, 2026cs.LG

Twist, Don't Tilt: Trajectory-Exact Constrained Decoding for Masked Diffusion Models

Constrained decoding for Masked Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constraint. MDLMs generate outputs by repeatedly unmasking masked positions present in their current state. Recent strategies for constrained decoding constrain the model's per-step mean-field posterior (which factorizes over masked positions) by enforcing the desired constraint with an automaton. The resulting chain-structured factor graph allows exact constrained sampling via dynamic programming. However, despite each draw being exact and constraint-satisfying, we prove that their composition, in general, tilts away from the model's relative probabilities over valid trajectories, thus leading to trajectory bias. We derive an exact expression for this bias as a product of ratios measuring how valid continuation mass changes when the denoiser is reconditioned, and characterize when the bias vanishes. We then correct the bias by introducing TWISTER, the first automaton-twisted Sequential Monte Carlo decoder for MDLMs, using the step-exact decoder as the proposal. We show that for regular language constraints, the Feynman-Kac correction is exactly computable, with the twists obtained efficiently using quantities pre-computed for step-exact sampling. We prove that the resulting Feynman-Kac model targets the unbiased Doob h-transformed path law conditioned on constraint satisfaction.

Aditya Thimmaiah, Lara Marinov, Jayanth Srinivasa +3

The University of Texas at Austin · Cisco Research

Constrained Decoding Masked Diffusion Models Language Model Decoding Diffusion Language Model Decoding

Sep 28, 2026cs.LG

Composable Decoding on the Probability Simplex: Theory and Implementation

Decoding for large language models is typically treated as a collection of isolated sampling strategies, with limited theoretical understanding of the behaviours they induce and how their underlying objectives relate. We formulate decoding as an optimisation problem over next-token distributions on the probability simplex, balancing expected model score against regularisation under support constraints. This view recovers familiar decoding methods through choices of regularisers and support constraints; more importantly, it enables new decoders to be constructed by composing distributional preferences within a single optimisation problem without external rewards, learned critics, or model parameter updates. We introduce CompoSimplex, a library with configurable support rules, regularisation primitives, and simplex solvers for constructing and evaluating compositional decoders. We evaluate standard samplers, individual regularisers, and compositions across multiple models and reasoning tasks. Our results show that compositions can realise trade-offs between single-sample quality, multi-sample quality, and diversity that are not attained by individual decoding objectives.

Xiaotong Ji, Ahmed Khaled Khamis, Rasul Tutunov +2

Huawei Noah’s Ark Lab · UCL Centre for AI

Constrained Decoding Language Model Decoding

Sep 27, 2026cs.LG

Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding

At each step, decoding one sequence with a large language model rereads the projection weights, whose traffic is fixed, and the key-value (KV) cache, whose traffic grows with context. Activation sparsity trims the first term and KV-cache sparsity the second, yet their reported speedups are hard to compare because each depends on context length and on the dense attention kernel it is measured against. We derive a byte crossover, the context length at which the two savings are equal, together with ideal speedup bounds for each branch and for their composition, from model dimensions and keep ratios alone. We then time both branches and their composition from 2K to 128K tokens on two GPUs after a dense prefill of real text, with dense and sparse modes reading the cache through the same split-K attention kernel. The projection branch leads at short context and the KV branch at long context, with speedups that follow their byte bounds up to fixed kernel costs. Adding these costs, measured in separate sweeps, lets the byte account predict the measured crossings of three keep-ratio pairs, a second model, and a second GPU to within 4.1K tokens. Timing the dense baseline with masked instead of split-K attention inflates the apparent speedup of the same KV policy about fivefold. An attention-scored KV selection answers the same passkey and multi-key placements as dense decoding up to 127K tokens, whereas a KV window misses most of them. Under matched perplexity budgets, activation sparsity composed with this selection decodes 14 to 26% faster than the best single branch on both GPUs. Code is available at https://github.com/js-lee-AI/ByteCross.

Jungseob Lee, Seungyoon Lee, Seongtae Hong +2

Korea University · Yonsei University Mirae Campus

Language Model Decoding Activation Sparsity KV-Cache Management LLM Inference Acceleration

Sep 24, 2026cs.CL

Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax

A language model can fail a syntactic test in two distinct ways: by not encoding the relevant structure, or by encoding it but failing to use it at the output. Behavioral evaluation alone cannot tell these apart. We propose a three-level evaluation framework (behavioral deployment, LM-head readout, and probe recoverability) measured on the same items under the same binary decision. Using a compact trilingual (English, Chinese, German) control-dependency benchmark, we find that probe recoverability exceeds or equals LM-head readout, which in turn exceeds or equals behavioral deployment, across seven models and all three languages in the aggregate. The recoverability surplus is never negative across all 14 (model, task) conditions. The disconnect concentrates in subject-control, where a nearest-noun heuristic gives the wrong answer. The single largest gap (0.653) appears on Qwen3-0.6B Instruct in question answering. The gap persists at Qwen3-14B Instruct. Instruction tuning degrades deployment more than encoding in percentage terms. We rule out option-position bias, late-layer erasure, output-formatting artifacts, and probe-training variance. The pattern is consistent with decoding that favors surface shortcuts, and the behavior-probe gap measures the strength of that preference. Activation patching shows the gap is layer-localized. Under instruction tuning, the LM-head-decoded layer shifts approximately ten layers later than the probe-decoded layer. These findings argue that behavioral evaluation understates what models encode, while probing alone overstates what they deploy.

Zhenyan Lu, He Wang, Xiaohui Huang

College of International Studies, National University of Defense Technology, Nanjing, China

LLM Evaluation Language Model Decoding Language Modeling Language Model Probing

Sep 24, 2026cs.CL

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the \textit{Superposition Linearity Hypothesis}. We provide evidence that superposition is an intrinsic property of the Transformer architecture rather than an emergent consequence of training; in fact, we observe that it tends to diminish as pretraining progresses. However, we demonstrate that linearity can be substantially restored through lightweight fine-tuning, significantly reducing the divergence between the predicted next-token distribution and the average of the individual next-token distributions. Finally, we introduce a guided decoding procedure that disentangles superposed outputs, enabling the simultaneous generation of two coherent continuations from a single forward pass.

Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk +6

Language Model Decoding Decoder-Only Language Models Representation Geometry in Language Models

Sep 23, 2026stat.ML

NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees

Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not directly provide numeri- cal values at a requested precision. We propose NUMERICJEV, a training-free numerical decod- ing algorithm that enables numerical output from any LLM with a Jev-like structured-choice in- terface. Surprisingly, on our arithmetic bench- mark, it outperforms direct selection from a can- didate list containing the correct answer by 2.93 percentage points (Figure 1). Our motivation comes from the observation that numerical range selection is itself a decision problem that Jev- like LLMs can address. NUMERICJEV recur- sively refines a range through a multiway deci- sion tree while retaining the original question in context, without parameter updates or hidden- state access. On a 100-value grid, a ten-way tree requires only two decision rounds. Range- normalized MAE is 1.84% versus 5.18% for di- rect choice. A separate three-date historical- index study yields 4.58% mean relative recall er- ror and 0% readout error when the value is sup- plied. Code is available at https://github. com/Bring-AI/jev-numeric.

Weiwei Ye, Hangchen Liu, Renhe Jiang

The University of Tokyo.

Numerical Reasoning in Language Models Language Model Decoding LLM Decision-Making

Sep 23, 2026cs.LG

FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation

Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it produces an increasing proportion of semantically duplicate answers as more samples are drawn, leading to diminishing returns. To address this limitation, we introduce FLEET, a novel method that integrates a memory mechanism into the generation process. FLEET represents each generation as a sparse trajectory through states whose entropy exceeds a predefined threshold and uses these trajectories to infer per-token utility scores that adjust the logits. Benchmark evaluations demonstrate that FLEET achieves the same accuracy as the repeated sampling baseline, with a 3x speedup, and substantially improves accuracy on complex coding tasks (LiveCodeBench Pass@32 increases from 59.9% to 66.2%) under the same budget. Furthermore, in the greedy-decoding configuration evaluated here, the approach is deterministic and uses a single calibration pass to derive its principal hyperparameters, requiring only minimal modifications to existing LLM pipelines.

Oleksii Streltsov, Oleksandra Vitko

Department of Artificial Intelligence, Kharkiv National University of Radio Electronics, Kharkiv, Ukraine

Language Model Decoding Memory-Augmented Language Models LLM Inference Acceleration LLM Code Generation

Sep 22, 2026cs.LG

Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference

Greedy decoding from large language models is commonly treated as deterministic. We show it is not precision-invariant: the same model, prompt, and decoding algorithm produce different outputs in BF16 versus FP16 on identical hardware. Across our evaluations of six models (1.1B-7B parameters, four families; divergence additionally characterised at 12B) and three benchmarks, 49-100% of prompts diverge; a single token flip often cascades into trajectory-level divergence. We develop an empirical error-propagation analysis and find that 22 layers of accumulated body error do not distinguish flipping from non-flipping steps; the outcome depends primarily on the top-two logit margin at the LM head relative to the directional perturbation between the top-two candidates. The analysis makes five testable predictions about intervention outcomes, including that applying more FP32 compute (broader scope) makes agreement worse. The experiments match all five predictions. The best-performing low-overhead intervention we evaluate, selective FP32 LM head recomputation, triggered only when the margin falls below a threshold, delivers +22-36 pp exact agreement on A10G (+12-21 pp on L4 and A100) at less than 4% latency overhead in low-batch (batch size <=4) single-stream inference. We map the applicability boundary across six models and four batch sizes, and hypothesise that training-time precision stability is a determining factor. The method is a partial mitigation rather than a universal determinism guarantee: its benefit vanishes when body-originated error dominates, including at batch size >=8 and under end-to-end FP8 in our tests.

Gaoyuan Du, Anam Nawaz Khan, Rex Zhou +4

University of Tennessee, Knoxville · University of Chicago · Amazon +1

Language Model Decoding LLM Inference LLM Reliability

Sep 17, 2026cs.CL

On-Demand Attention: Language Models Know When to Recall

Reasoning and agentic workloads increasingly demand efficient long-context inference. Yet full-attention decoding reads the growing history at every step, regardless of its benefit to the next prediction. We show that a pretrained model's decoding states already contain information predictive of this benefit, before the global read. Building on this finding, we introduce On-Demand Attention (ODA), a local-first decoding method that uses a lightweight recall head to selectively invoke global attention as its predicted benefit changes during generation. ODA trains only the recall head, leaving pretrained weights unchanged and the complete historical KV cache available for future recall. We further implement GPU-side conditional execution in vLLM, translating reduced global reads into practical decoding speedups over full attention at long context lengths. Experiments across Qwen and Gemma models, including hybrid-attention backbones, show that selective recall recovers most of the performance lost under local attention while substantially reducing global reads. These findings support long-context inference in which pretrained models guide their own access to the information they retain.

Haibo Feng, Ruiqi Liang, Hanyang Peng +1

Southern University of Science and Technology · Peking University · Peng Cheng Laboratory

Language Model Decoding Long-Context Language Model Inference LLM Inference Acceleration Attention Mechanisms

Sep 16, 2026cs.AI

Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning

We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large Language Model (LLM) decoding framework that frames candidate token selection as ensemble pruning. Existing selection strategies rely predominantly on scalar probabilities, ignoring geometric semantic relationships and causing candidate redundancy. Meanwhile, current geometry-aware methods often require complex optimization or directly reweighting the original token probabilities, leading to significant computational overhead or inference instability. To address this, we formulate decoding as a subset optimization problem using a Mahalanobis distance-driven objective to enhance semantic diversity while preserving high probabilities. Specifically, we dynamically discount redundant generation paths using a token similarity matrix, constructed via an adaptive-bandwidth kernel over token embeddings. We further devise an efficient greedy selection algorithm with near-linear complexity in the candidate size under early stopping, while establishing its theoretical approximation guarantees. This renders ME-Decoding a robust, plug-and-play module with negligible inference overhead. Extensive experiments across diverse reasoning and generation tasks demonstrate that our method consistently achieves strong performance.

Dunyao Xue, Chengshuo Du, Zhengbo Wang +2

Institute of Statistics and Big Data, Renmin University of China, Beijing, China · Big Data and Responsible Artificial Intelligence for National Governance, Renmin University of China, Beijing, China · Center for Applied Statistics, Institute of Statistics and Big Data, Renmin University of China, Beijing, China

Language Model Decoding Diverse Text Generation

Sep 14, 2026cs.CL

Look Before You Leap: Factual Decoding with Internal Attribution Signals

Hallucination remains a critical challenge in large language models (LLMs), where early factual errors compound through autoregressive generation in a snowballing effect that neither post-hoc correction nor weight-level intervention can effectively preempt. We propose DescaPE (DEcoding Signal Control Against Path Error-snowballing), a decoding framework that leverages internal model signals to suppress hallucination-prone trajectories at inference time. Through sliding-window MLP ablation, we identify a factual-salient layer span within LLMs whose derived signal is selectively elevated for factual tokens and exhibits anomalous spikes at hallucination-prone steps. We train a lightweight probe to approximate this signal from a single forward pass and integrate it into candidate scoring to penalize high-risk continuations while rewarding factually grounded ones. Experiments across five factuality benchmarks on three LLMs demonstrate that DescaPE achieves factuality improvements over decoding-time baselines in multiple settings, while incurring only 1.10x latency overhead in our efficiency evaluation. Our code is available at https://github.com/hayeonggg/DESCAPE.

Hayeong Ryu, JungMin Yun, Byeonggeuk Lim +2

Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University

Language Model Decoding Language Model Error Detection LLM Hallucination Mitigation

Sep 14, 2026cs.CL

Temperature Fragility and the Conditional Benefits of Truncation Sampling

Large language models generate text by sampling each token from a predicted distribution, and a temperature parameter sets how far the draw strays from the most probable tokens. Truncation samplers such as top-p and min-p discard the least probable tokens before the draw, so that sampling at high temperature stays coherent. Their reported accuracy gains come from temperatures of 1.5 to 3, while the defaults of deployed systems cluster between 0.6 and 1.0. Whether they change accuracy at those defaults, and for which models, has not been measured. We test thirteen open-weight models on GSM8K and MMLU-Pro at temperatures 0.7, 1.0, and 1.3 in one controlled pipeline, ten of them under eight decoding configurations. Six of the thirteen models lose 17 to 38 accuracy points on MMLU-Pro between 0.7 and 1.3, and the other seven lose at most 10. The lost accuracy comes from generations that run to the token limit or never state an answer. These results suggest that truncation samplers improve accuracy primarily when higher temperatures substantially degrade model performance. Where accuracy remains stable across temperatures, none of the tested truncation samplers improves on plain temperature sampling.

Francesco La Rosa

University of Edinburgh

LLM Evaluation Language Model Decoding

Sep 14, 2026cs.CL

Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding

Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-training. However, many existing SMC approaches rely on equal-weight resampling, which can aggressively prune low-weight trajectories, discarding potentially correct reasoning paths and degrading the genealogical diversity of the search space. To address this, we introduce Chopthin-Consensus Power Sampling (CCPS). Our method applies the Chopthin resampler to LLM decoding: rather than equalizing weights and forcing unnecessary particle duplication, it enforces an upper bound on the ratio between the largest and smallest weights and carries the unequal weights forward. This targeted intervention preserves a richer set of distinct reasoning paths, keeps the weighted SMC approximation unchanged in conditional expectation, and guarantees a lower bound on the post-resampling effective sample size (ESS). To fully exploit this enriched population, we employ a semantic-majority selection mechanism that merges token-identical final trajectories, clusters semantically equivalent answers, and returns the answer supported by the largest number of distinct trajectories. Evaluating across three open-weight models and five reasoning benchmarks, we show that Chopthin increases oracle coverage in 13 of 15 settings. Combined with semantic-majority selection, CCPS matches or exceeds the final-answer accuracy of the Power-SMC baseline in 14 of 15 settings, delivering absolute gains of up to 10.6 percentage points. These findings demonstrate that diversity-preserving resampling and diversity-aware selection are complementary mechanisms for training-free LLM reasoning. Code is available at github.com/MinooAhmadii/chopthin-consensus-power-sampling.

Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo +2

University of Southern California, Los Angeles, USA

Language Model Decoding LLM Inference LLM Reasoning

Sep 13, 2026cs.CL

Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for Reliable Clinical LLM Answer Selection

Large language models (LLMs) are often deemed unsafe for clinical question answering because of their tendency to hallucinate. Retrieval augmentation, fine-tuning, and external verifiers require new infrastructure that clinical governance must approve and may add latency or extra model calls. Inference-time correction uses the model's internal logit signals, but a fixed transformation need not suit every question. A corrector that improves accuracy by about ten percentage points on a truthfulness stress test yields negligible gains on clinical multiple-choice benchmarks, where instruction tuning concentrates output probability on one answer and leaves low terminal entropy. We introduce ALTAS, which reads terminal entropy and late-layer linearity (

R^2

) from one forward pass to choose per question between greedy decoding and late-layer trajectory correction. No classifier, probe, or head is trained; the router operates on candidate-answer logits and adds 6.5% latency overhead. Applied to every question, the correction improves TruthfulQA over greedy at 3B and 8B by 11.4 and 10.0 percentage points, respectively (

p<10^{-10}

). Gated per question, ALTAS retains gains of 8.3 to 9.5 percentage points while keeping MedQA, PubMedQA, and MedHallu within a one-percentage-point do-no-harm band, with no statistically significant differences from greedy. The method passes verification sweeps over frozen thresholds, the scoring rule, and the domain label.

Zeyu Dong, Benjamin Wang, Joyee W. Jin

St. Theresa of Lisieux Catholic High School Toronto, Canada · Department of Computer Science University of Toronto Toronto, Canada

Adaptive Inference Language Model Decoding LLM Hallucination Mitigation LLM Routing Medical LLMs

Sep 7, 2026cs.CL

Line-Coupled Language Model

Autoregressive language models generate one token per decoding step, limiting the useful output of each forward pass. Although diffusion models, insertion-based decoding, and multi-token prediction enable parallel generation, they either incur additional training-time token traffic or struggle to predict strongly dependent future tokens. We introduce the Line-Coupled Language Model (LCLM), an autoregressive model that advances multiple text lines together by predicting the next token for every active line while coupling the lines through shared causal context. LCLM interleaves line tokens into a single causal sequence and uses line-staggered rotary positions, retaining the standard next-token objective and causal attention. Controlled experiments show that cross-line targets are substantially less dependent than consecutive same-line targets, supporting lines as parallel generation units. With 881M parameters, LCLM produces an average of 2.94 content tokens per forward pass with a validation cross-entropy loss of 2.44, compared with 1.00 token per forward pass and a loss of 2.39 for the vanilla autoregressive baseline. Most notably, even when LCLM generates 16 tokens per forward pass, its loss is only 0.09 higher than that of the vanilla autoregressive baseline (2.34 vs. 2.25).

Shiyuan Li, Shaorong Zhang, Zhaorui Yang +3

University of California, Riverside Riverside, CA, USA

Multi-Token Prediction Language Model Decoding Autoregressive Language Modeling Autoregressive Decoding

Sep 2, 2026cs.CL

Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models

Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive paradigm. With bidirectional attention and any-order generation, DLMs naturally fit infilling tasks, which require generating a middle span conditioned on both the prefix and the suffix. However, infilling is sensitive to the length of the span, while DLMs require the length to be fixed before generation. Although prior studies extend DLMs to dynamic lengths, they still suffer from two limitations. (i) Sensitivity to initial length. These methods require a preset length to initialize the search and are highly sensitive to this initial length, often yielding suboptimal results. (ii) Inference inefficiency. They either insert length-changing operations during generation or repeatedly search for an appropriate length using multi-step denoising confidence, both of which introduce substantial extra forward passes and computational cost. Therefore, we propose PILL (Probing-based InfiLling with preset-Length-free decoding), an efficient infilling method for DLMs that requires no preset initial length and adds far fewer extra forward passes than baselines, substantially reducing inference time. Experiments show that, across five DLMs spanning different families, architectures, and training recipes on eight infilling benchmarks, PILL improves over the strongest baseline by +4.8 average pass rate on code and +6.0 BLEU-2 on text, while running 1.82x faster than that baseline. The code is available at https://github.com/Hsu1023/PILL.

Haobo Xu, Sirui Chen, Yuanchen Bei +5

University of Illinois at Urbana-Champaign · Meta

Language Model Decoding Diffusion Language Models Efficient Inference

Sep 1, 2026cs.LG

hLLM: Single Pass Decoding for Generative Reranking

Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive decoding spends one sequential forward pass per emitted token. We observe that the only tokens a ranker must emit are the

N

ordinal values naming the items in ranked order, and that this narrow, permutation-structured output format admits decoding strategies which are much more efficient than left-to-right generation. We introduce hLLM (Hungarian LLM), a format-specialized decoding strategy that decodes all

N

ordinals in

O(1)

forward passes. hLLM reads an

N \times K

item-position score matrix off the LLM's prefill hidden states with a lightweight self-attention head, then decodes the ordinals as the optimal bipartite assignment of that matrix via the Hungarian algorithm, yielding a valid permutation by construction rather than by repair. Through a systematic study of training signals and backbone adaptation, we show that LoRA-based fine-tuning combined with teacher ranking distillation reaches 28 ms end-to-end inference, a speed-up of

64\times

while maintaining ranking quality on par with the teacher. We provide a complete ablation decomposing the contributions of architecture, training signal, and backbone adaptation. Our framework connects generative ranking to combinatorial optimization, opening a path toward other

O(1)

-decode mechanisms for real-time ranking.

Emil Laftchiev, Prachi Agrawal, Moe Kayali +7

Meta Platforms, Inc.

Language Model Decoding LLM Reranking LLM Inference Acceleration

Sep 1, 2026cs.CL

Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding

Minimum Bayes Risk (MBR) decoding enables high-quality text generation by selecting the hypothesis that maximizes a utility metric over sampled pseudo-references. However, it is highly susceptible to metric overfitting: it can irregularly inflate the chosen utility metric at the direct expense of other unoptimized evaluation metrics. To mitigate this, we introduce SVD-MBR, which frames the pairwise utility matrix as a noisy information signal. By computing a low-rank approximation via Singular Value Decomposition (SVD) and retaining only the top-

k

components, we effectively decouple true consensus from metric noise. Experiments demonstrate that SVD-MBR successfully regularizes decoding, yielding substantial gains across a range of generalized metrics. Furthermore, we reveal that this denoising is metric-dependent: neural metrics encode a robust low-rank consensus ideal for SVD, whereas surface-level metrics struggle to separate signal from metric noise.

Riza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito +2

Nara Institute of Science and Technology (NAIST) · The University of Tokyo

Language Model Decoding MBR Decoding

Aug 24, 2026cs.AI

Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance

Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably leading to alignment failures. This work systematically investigates instances where LLMs fail to exhibit ethical behavior. To understand the underlying mechanics of these vulnerabilities, we introduce a probing methodology that presents unethical scenarios to LLMs in three distinct structural modalities: objective classification tasks, subjective first-person statements, and direct requests for assistance. We find that model performance degrades in the request-for-assistance-based form. Using Layer-wise Relevance Propagation (LRP), we trace this discrepancy to an attribution bias: the model places greater emphasis on benign task-framing tokens (e.g., "Can you help me...") than on tokens signaling the underlying unethical behavior (e.g., "without getting caught"), which we term cue-tokens. We hypothesize that this under-attribution contributes to harmful compliance. To test this, we introduce two LRP-guided decoding methods that steer generation toward trajectories more relevant to cue tokens. Empirical evaluations show that these interventions promote safer responses, supporting cue-token attribution's role in compliance failures.

Or Biton, Tomer Krichli, Itai Allouche +1

Faculty of Electrical and Computer Engineering, Technion, Haifa, Israel

Language Model Decoding Language Model Safety Evaluation LLM Interpretability LLM Safety

Aug 12, 2026cs.CL

Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models

Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding. We identify a ripple effect in dLLM decoding: proactively committing a mid-entropy pivot position can induce a pronounced reduction in uncertainty across the remaining masked positions. This uncertainty reduction allows subsequent steps to unmask more tokens in parallel, thereby accelerating the overall decoding process. To exploit the ripple effect, we propose Ripple-Pivot Search (RPS), a novel training-free decoding method that seeks mid-entropy positions as promising candidate pivots (where to decode), and determines their token assignment that yields the greatest downstream benefit via lookahead evaluation (what to decode). Across 3 dLLMs and 4 reasoning and code-generation benchmarks, RPS achieves 4-10

\times

wall-clock speedup over the standard decoder while preserving generation quality, and improves accuracy over the previous lookahead baseline by up to 5.49% while delivering higher throughput in most settings. When integrated with KV caching, RPS further achieves up to 18

\times

wall-clock speedup over the standard decoder.

Yushi Ye, Xu Chen, Haoyun Jiang +7

Cooperative Medianet Innovation Center, Shanghai Jiao Tong University · Alibaba Group · TMLR Group, Department of Computer Science, Hong Kong Baptist University +2

Language Model Decoding Diffusion Language Model Inference Parallel Decoding Diffusion Language Model Decoding

Aug 11, 2026cs.CL

Decomposition-Induced Context-Memory Conflict: When Fact-Checking Pipelines Contradict Their Own Source Text

Decompose-then-verify pipelines, including FActScore-style fact-checkers and long-form factuality evaluators, first split a passage into atomic claims before checking each one. Decomposition itself is treated as a neutral preprocessing step. We show it is not: a decomposer can be induced to substitute its own parametric belief for what the source passage says, producing a claim that contradicts the text it was supposed to summarize faithfully. We call this Decomposition-Induced Context-Memory Conflict (DI-CC) and show it is mechanistically the same phenomenon as classical context-memory conflict, occurring inside a different pipeline stage than prior work has examined. A linear probe trained only on classical context-memory conflict data (NQ-Swap), never exposed to any decomposition output, significantly separates decomposition positions that produce DI-CC from faithful decompositions (AUC = 0.86-0.88, permutation p < 0.0005). An existing reference-free baseline, SelfCheckGPT-style self-consistency sampling, fails to detect DI-CC at all (AUC 0.51, chance-level), because DI-CC content is stably recoverable and recurs across resamples, unlike the variability self-consistency methods rely on. Context-aware decoding, a training-free mitigation from the classical setting, transfers to decomposition and suppresses DI-CC, but at a severe cost: many decompositions under coreference-heavy conditions fail to parse, often because the decomposer fabricates a different identity. We do not consider this mitigation deployment-ready. We further characterize the mechanism's boundaries: its natural occurrence rate is too sparss not manifest on naturally-occurring hallucinatedtext, and it requires a minimum model scale to detecablish DI-CC as a real, mechanistically grounded, andpartially treatable failure mode, with a scope we chhan overstate.

Yu-Feng Yen

Independent Researcher

Language Model Decoding Knowledge Conflicts in Language Models Factual Consistency Evaluation

Aug 7, 2026cs.CL

FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding

Token-level collaboration allows a large language model (LLM) to assist a small language model (SLM) when their predictions diverge. Existing methods either use LLM-generated intervention tokens or rank candidates with the LLM's next-token probabilities. Both rely on the LLM's local preference, even though an LLM-selected token may be difficult for the SLM to build on. We present FutureBridge, which ranks joint LLM-SLM token candidates according to how well they support the SLM's subsequent reasoning. During training, an answer-verified LLM trajectory supplies a fixed shared future, and a frozen SLM evaluates every candidate under this common context. The resulting counterfactual scores supervise a lightweight token reranker that observes only the current state and candidate token. At inference, FutureBridge uses the LLM only to expand the candidate pool, selects one token, and returns generation to the SLM without generating or appending a future suffix. Across five mathematical reasoning benchmarks, FutureBridge improves the Qwen3-1.7B SLM's Math Avg. by 35.1% relative to greedy SLM decoding. These results indicate that token selection benefits from modeling whether the receiving SLM can use each candidate to continue reasoning, rather than relying on the LLM's local preference alone.

Quanquan Li, Hongbo Zhang, Yihe Chi +9

1East China Normal University · 2Peking University · University of Science and Technology of China +3

Language Model Decoding Multi-LLM Collaboration

Aug 2, 2026physics.soc-ph

Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs

Increasing the temperature of an ordinary many-state system increases access to a wider range of states and hence increases its entropy. We find the opposite in ChatGPT-like AIs, even though raising the decoder temperature likewise increases access to a wider range of states (next-token choices). Across 12,000 continuations from 11 AIs, autoregressive feedback drives the long-time output population through an entropy maximum and into population inversion. The transition features frozen states, cycles, intermittency and noise-induced ordering. We present evidence of a hidden coordinate that acts as the state variable of an effective nonlinear map. Its trajectory average strongly predicts output repetition in separate test trajectories. ChatGPT-like AIs therefore behave not as `stochastic parrots', but as a new class of controllable nonlinear physical systems whose internal dynamics can be measured and perturbed.

Neil F. Johnson, Frank Yingjie Huo, Bella Xinrui Li

Department of Physics, The George Washington University Washington, DC 20052, USA

Language Model Decoding Autoregressive Generation Data Repetition in Language Model Training

Jul 28, 2026cs.AI

Instruction-Tuned Language Models Cannot Sample from Distributions They Can Describe

Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution. We show this draw does not exist: instruction-tuned models do not sample from distributions, they collapse to a single output. The same persona on the same question returns the same answer on more than half of items in a public-opinion benchmark, and the model's internal probabilities concentrate on a single option. The failure is associated with, and amplified by, instruction-targeted post-training: instruction-tuned models are worse than their own bases in every family we can compare, the gap widens at each successive post-training stage and with the size of the tuning update, and continued pretraining on non-instruction tokens leaves it unchanged. Yet the knowledge survives: the same model that cannot sample from a distribution can describe it accurately in a single call. We call this gap the KNOWS/DOES split. Exploiting the split, a single call that asks the model to describe the response distribution more than halves the error against human survey data compared to persona aggregation. When per-persona outputs are required, we propose Prompt-Perturbed Argyle (PPA), which reduces the same error by 21%, spreading each persona's answers to mirror real population differences at no added cost.

Chaemin Jang, Dongman Lee, Jihee Kim

School of Computing, KAIST · School of Business and Technology Management, KAIST

Language Model Decoding LLM Prompting LLM Fine-Tuning User Simulation

Jul 27, 2026cs.AI

Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

Semantic IDs (SIDs) are now a central component of generative recommendation. Current SID-based systems assign three roles to the same token sequence. Shared prefixes are intended to organize related items, the complete SID identifies an individual item, and each generated token narrows the items that can still be returned. We systematically investigate SIDs from item encoding and SID construction to autoregressive generation and final recommendation. We examine how SID construction changes item representations and how those changes affect generation. Across three Amazon domains and eight SID constructions, SID neighborhoods recover only 32.2% of the encoder's ten nearest neighbors on average. Alternative item descriptions still retrieve the corresponding item first in 99.57% of controlled cases, yet change 38.4% of exact SIDs. These results show that SIDs retain broad organization but lose much of the encoder's fine local structure, while their exact tokens are not determined by item meaning alone. This loss becomes consequential during generation. After the final semantic token, TIGER retains only 29.9% of held-out targets that were plausible recommendations before SID filtering. Motivated by these findings, we propose Item-Supported Decoding (ISD), a lightweight inference-time method that allows a user-specific item ranking to support corresponding SID prefixes before beam search discards them. The same ranking then orders the generated items. ISD requires no additional parameters or retraining of the SID constructor or decoder. We empirically show that ISD improves NDCG@10 over the corresponding SID backbone in every evaluated setting, with relative gains of up to 31.2%. Our results show that SIDs provide useful coarse item organization, but their fine boundaries should not alone determine which items remain available during generation.

Junting Wang, Xinrui He, Yunzhe Li +1

University of Illinois Urbana-Champaign Urbana, Illinois, USA

Semantic ID Recommendation Language Model Decoding Generative Recommendation

Jul 27, 2026cs.CL

SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding

Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, formats, and safety requirements. However, models follow these prompts only implicitly through in-context learning, which can be insufficient for complex or compositional prompts. Existing approaches often require model tuning or response-level reranking, limiting their practicality for lightweight inference-time control. We introduce SyRuP, a decoding-time framework for improving system-prompt adherence while keeping the base LM frozen. SyRuP trains a cross-attention reward head from system-prompt-conditioned preference pairs, treating the system prompt as a separate memory to produce token-level adherence scores. At inference, SyRuP reranks the base LM's top-k candidates by combining base logits with both the learned reward signal and a contrastive signal that captures system-induced logit shifts. Experiments on system-prompt following benchmarks show that SyRuP consistently outperforms prompting and decoding-time baselines with moderate inference overhead. These results suggest that explicit token-level guidance is an effective and practical mechanism for reliable system-prompt following.

Seoyeon Kim, Minjae Kang, Jaehyung Kim

Yonsei University

Language Model Decoding Language Model Steering Instruction Following

Jul 22, 2026cs.AI

Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling

Recent advances in truncation-based sampling have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater diversity without sacrificing coherence. However, increasing the entropy of the token probability distribution via high temperatures has also been shown to weaken the model's refusal response. Existing solutions for maintaining the refusal behavior of LLMs either replace the model's own refusal decision with a separate safety classifier or alter its output distribution for every prompt. To address this gap, we propose refusal-gated decoding (RGD): an efficient sequential decoding approach which preserves a model's greedy decoding refusal response at high temperatures and samples all other prompts from its exact direct high-temperature distribution, while incurring minimal additional latency. RGD runs a short greedy probe that reuses the prompt's KV cache and exits as soon as it becomes incompatible with a learned set of refusal prefixes; it returns the greedy response if the probe remains compatible and otherwise discards the probe and samples from the original prompt. Across seven models and three benchmark datasets at T=2.0, RGD raises greedy-refusal preservation from 91.9% under direct sampling to 98.3% on average while adding only 2.2-4.3% to the median per-request latency of non-refusals across temperatures. Unlike prompt-screening baselines which route many greedy non-refusals to greedy decoding, RGD keeps at least 98.1% of greedy non-refusals on unchanged high-temperature sampling, thereby preserving the model's natural high-temperature sampling behavior. We also propose a residual-stream variant of our method which lowers this latency overhead to at most 0.5% with comparable prompt routing accuracy. Our work shows that unlocking greater diversity via high-temperature sampling need not erode a model's refusal behavior.

Phillip Howard, Xin Su, Allen Roush +3

Thoughtworks

Language Model Decoding LLM Refusal Behavior Refusal Behavior in Language Models

Jul 21, 2026cs.CL

Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models

Diffusion language models (DLMs) can revise tokens bidirectionally, but standard decoding procedures often adapt them to left-to-right generation by producing text block by block. We study a simple plug-and-play inference pattern: first generate a complete draft, then refine the full response using bidirectional diffusion. Using LLaDA2.1-Flash and LLaDA2.1-Mini, we evaluate two configurations. In Flash-Flash, the same Flash model serves as both drafter and refiner, testing whether an existing model can improve its own block-autoregressive output through global refinement. In Mini-Flash, inspired by speculative decoding, we introduce speculative correction: Mini drafts a full response, and Flash revises it as an editable initialization. Flash-Flash improves GSM8K-384 accuracy from 0.848 to 0.899 while running 1.20 times faster than the selected Flash block-autoregressive baseline, and improves MBPP-384 from 0.545 to 0.693. Latency-window-matched Flash-only controls indicate that these gains persist after targeted tuning of block-autoregressive decoding. Causal ablations indicate that completed drafts provide useful initializations: refinement from a fully masked span performs poorly, full global refinement provides a clear additional gain on GSM8K, and local refinement captures much of the gain on MBPP and MATH. Mini-Flash provides useful quality-latency trade-offs, including MATH-384 performance of 0.294 versus 0.300 for Flash while running 2.17 times faster. These results support a Pareto-frontier interpretation rather than the claim that the heterogeneous cascade uniformly matches Flash quality. Overall, same-model draft-and-refine provides evidence that bidirectional refinement is a useful decoding primitive for DLMs, while speculative correction demonstrates a training-free route to fast DLM generation.

Brian K Chen, Chong Wu, Kenji Kawaguchi

National University of Singapore · City University of Hong Kong

Language Model Decoding Speculative Decoding for Diffusion Language Models Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration

Jul 17, 2026cs.AI

Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models

Attention collapse in autoregressive language models -- manifested as repetitive token loops where the model becomes trapped in self-reinforcing attractors -- is a persistent pathology that existing decoding-time heuristics fail to address at its root cause. We present a principled framework that penalises or compensates anomalous confidence arising from collapsed generation patterns, by comparing a token's observed frequency against its corpus prior through an adjacent-conditional probability construction. The resulting self-normalising penalty ratio

R=f(m,n,p)/f(np,n,p)

requires no ad hoc standardisation and admits a closed-form logit offset with zero approximation error. The correction is isolated from the loss gradient and accumulated into a frozen output-layer bias via exponential moving average, enabling deployment as a repair mechanism for models that have already collapsed without requiring intrusive modifications to standard training pipelines. Experimental validation on a 1.5B-parameter model demonstrates that the frozen-bias mechanism can rescue a model already trapped in a collapsed attractor, reducing 2-gram repetition from 0.073 to near 0 while preserving generation quality.

Wenjie Fan, Bin Ma, Dong Li

Yotta Labs

Language Model Decoding Autoregressive Language Modeling Text Generation

Jul 17, 2026cs.CL

Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models

Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding. Recent lookahead-based decoding methods improve the accuracy--efficiency trade-off by exploring future decoding states before committing token updates. However, existing approaches mainly rely on shallow one-step lookahead, which optimizes immediate information gain but can be suboptimal for longer-horizon decoding trajectories. Meanwhile, we find that a naive extension for deeper lookahead is also ineffective, as fixed-depth rollout introduces additional computation and cannot adapt to heterogeneous intermediate decoding states. Thus, in this work, we propose AdaLook, an adaptive lookahead framework for DLM decoding. AdaLook dynamically determines whether to continue rollout based on candidate-score variance and further enables branch expansion when intermediate rollout states require additional exploration. This design avoids unnecessary deep rollout while allowing the decoder to re-trigger lookahead from informative intermediate states. Experiments on various benchmarks and models demonstrate that AdaLook achieves a better accuracy--decoding steps trade-off than existing one-step lookahead decoding methods.

Yingqian Cui, Wei Deng, Lantao Mei +4

Michigan State University · Morgan Stanley · IBM T.J. Watson Research Center

Masked Diffusion Models Language Model Decoding Diffusion Language Model Decoding Diffusion Model Inference Acceleration

Jul 13, 2026cs.AI

Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors

Low-bit quantization makes small reasoning models inexpensive to deploy but can degrade their chains of thought. This motivates decoder-side monitors that intervene when generation becomes unreliable. We show that a natural candidate, the centered token log-probability increment

\log p(w_t)+H_t

, is the wrong observable for this purpose. Under the model's own sampling law it is a mean-zero martingale by construction, so it measures sampling self-consistency rather than trajectory health and is nearly silent during confident repetition, where both

\log p(w_t)

and entropy are close to zero. We introduce a training-free decoding controller that combines (i) a degeneration-aware alarm score fusing token uncertainty with explicit verbatim repetition and (ii) a calibrated e-process-inspired sequential detector. The raw product process is Ville-valid under a conditional-mean null, while the deployed CUSUM-floored statistic is treated as an empirical change detector because the score is history-dependent and autocorrelated. On GSM8K with DeepSeek-R1-Distill-Qwen-1.5B in FP16 and INT4, calibration turns a monitor that fires on 93--95% of generations into a selective detector of failing traces (

φ\approx 0.3

, precision

\approx 0.6

against a 0.38 base rate). In this pilot, the controller reduces measured verbatim-degeneration signals and yields a positive but statistically inconclusive INT4 accuracy change from 63% to 69% (paired McNemar

p=0.18

,

n=100

), at a 28% token-budget cost. We also find that non-termination, rather than looping, is the dominant failure mode on GSM8K. The main contribution is methodological: an explanation of why centered token log-probability is inadequate for decoder monitoring and a calibrated, cautiously evaluated replacement.

El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan +1

Novelis Research, Paris, France

Language Model Decoding Change-Point Detection

Jul 9, 2026cs.LG

Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls

The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama

.

cpp, and a dozen further engines) branches on the sign of each raw logit (divide positives by theta, multiply negatives). But the softmax is unchanged by adding a constant to every logit, so a model's logit zero-point is arbitrary (a gauge choice), and the sign-branch reads it. Two measurable consequences follow. (1) The penalty is not well-defined: re-centering a model's logits by a constant is a provable no-op at theta=1, yet at a routine theta=1.3 it changes 58-96% of greedy tokens, while subtractive and normalized penalties change none; real checkpoints sit at widely different zero-points, so a fixed repetition_penalty is a different operation on every model. (2) It corrupts structured output: on 200 real-world JSON schemas, theta=1.3 drops the rate of valid, schema-conformant output from 97% to 23%. Applying the penalty to normalized log-probabilities instead of raw logits removes the gauge dependence by construction; HuggingFace's beam search has applied its processor chain, penalty included, to log-probabilities since at least v4.0.0, so repetition_penalty already names two different operators depending on decoding strategy. Because equal theta is not equal strength across the two operators, we also compare them at matched suppression, calibrated per model by search: there the normalized operator is statistically no worse on any quality metric measured, but on four of seven models it cannot match the raw operator's suppression at theta >= 1.15, and on six of seven at theta=1.3, the setting where the corruption was measured. This note gives the mechanism, the measurements (five models up to 7B; two code models; both effects replicated inside vLLM and llama

.

cpp through their own samplers), the per-model calibration map, and the normalized variant.

Peter Hollows

Language Model Decoding LLM Inference LLM Reliability

Jul 6, 2026cs.LG

Noisy-Channel Minimum Bayes Risk Decoding

Minimum Bayes Risk (MBR) decoding yields more robust and higher-quality text generation than maximum a posteriori (MAP) decoding by selecting hypotheses that maximize expected utility over sampled pseudo-references. However, there exists a discrepancy in the design: hypothesis selection calculates expected utility scores conditioned on given pseudo-references, while commonly used evaluation metrics, e.g., BLEU and COMET, are asymmetric. Therefore, it is important to consider both hypothesis-to-reference and reference-to-hypothesis directional effects. In this study, we introduce a noisy channel decomposition of MBR decoding that naturally incorporates bidirectional effects to account for these asymmetries. We decompose MBR decoding into four interacting components: hypothesis-to-reference likelihood, reference-to-hypothesis likelihood, hypothesis prior, and reference prior. This decomposition provides a unified interpretation of existing MBR variants and enables metric- and task-specific interpretability by isolating the contribution of each channel. Our comprehensive analysis reveals that channel-wise contributions exhibit distinct characteristics across metrics while remaining consistent across tasks, and suggests that appropriate channel weighting may lead to improvements over original MBR decoding.

Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

Nara Institute of Science and Technology, Nara, Japan.

Language Model Decoding MBR Decoding

Jul 3, 2026cs.LG

What Does a Routing Oracle Measure Under Stochastic Decoding? Coupling, Scorer Choice, and Single-Commit Ceilings

Routing benchmarks often compare a policy that commits to one model before seeing its response with a hindsight oracle that credits any correct recorded output. Under stochastic decoding these are different decision classes. For success marginals

p_{im}

under a frozen query--model--decoder--scorer protocol, we distinguish the clairvoyant single-commit ceiling

R_i=\max_m p_{im}

, product-coupling union

U_i^\perp=1-\prod_m(1-p_{im})

, and premium

Δ_i^\perp=U_i^\perp-R_i

. The marginals alone identify exactly the union interval

[R_i,\min\{1,\sum_m p_{im}\}]

: zero premium is attainable over compatible couplings, not established for an actual deployment. If generation is independent across models, product is the specified protocol's union probability. We audit frozen correctness tensors from 11 open models and 30 archived responses per query--model cell on GSM8K, MATH-500, and GPQA-Diamond. Full-pool display-channel product premiums are 0.371, 3.542, and 5.100 percentage points; the premium intervals from empirical marginals are

[0,0.473]

,

[0,4.787]

, and

[0,7.744]

. Their zero lower endpoints are algebraic. All retained scorers, eight finite-draw paths, and all 2,047 nonempty subpools expose scorer, estimator, and pool sensitivity, not confidence intervals. The GSM8K and GPQA display scorers were developed after limited output inspection. A separate retrospective held-out policy illustration instantiates the policy-specific gap decomposition without establishing new-data generalization. A limited reference-based human check supports scorer agreement only on definite-consensus subsets. Hash-bound evidence supports number checks, not end-to-end reproduction. The contribution is a measurement contract for interpreting oracle gaps conditional on coupling, decision class, scorer, pool, and finite draws, not a population effect or an equal-cost routing gain.

Teng-Ruei Chen

Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan · Krixvon AI, Taiwan

LLM Evaluation Language Model Decoding LLM Routing

Jul 2, 2026cs.LG

Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding

Discrete diffusion models have steadily improved in quality relative to autoregressive (AR) models. However, these models are normally constrained to fixed-length generation and do not support key-value (KV) caching. Block diffusion partially bridges diffusion and AR by generating token blocks left-to-right, but its fixed-size sequential blocks limit decoding flexibility and parallelism. Here, we present a new class of language models, set diffusion, comprised of (i) a likelihood parameterization that factorizes over flexible-position, flexible-length token sets and (ii) a set-causal diffusion architecture that supports KV cache updates after every inference step. By factorizing over token sets instead of fixed-size blocks, tokens can be decoded in arbitrarily-ordered sets, including sliding-window sets, enabling faster inference and support for any-order decoding. Set diffusion achieves better speed-quality tradeoffs on mathematical reasoning, summarization, and unconditional generation compared to prior diffusion language models while offering stronger infilling performance than block diffusion. We provide the code, along with the model weights and blog post on the project page: https://m-arriola.com/setdlms/

Marianne Arriola, Volodymyr Kuleshov

Department of Computer Science, Cornell University, Ithaca, NY, USA.

Language Model Decoding Diffusion Language Model Decoding Diffusion Model Caching Diffusion Language Models Diffusion Model Inference Acceleration Diffusion Models

Jun 28, 2026cs.LG

Depth Exploration for LLM Decoding

Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths. Existing lossless depth-adaptive methods exploit this redundancy by choosing a single non-final exit depth and verifying its prediction with the final-depth model. However, our measurements show that this selection-based strategy leaves substantial headroom: choosing an exit too late wastes computation, while choosing one too early triggers fallback and discards dependent drafts. We propose Depth Exploration Decoding (DEX), a lossless decoding algorithm that replaces single-depth selection with parallel exploration over multiple candidate depths. At each commit position, DEX validates candidates against the final-depth reference, commits exactly the final-depth token, and collapses the exploration lattice to retain only reusable branch states. This expand--commit--collapse procedure preserves equivalence to standard autoregressive decoding while reducing the cost of committing each token. Across early-exit-trained and standard LLMs, DEX outperforms representative depth-selection baselines and achieves competitive end-to-end throughput against speculative and distributed decoding methods. Moreover, DEX improves as the explored depths become finer, showing that parallel depth exploration provides a scalable way to exploit the underused depth axis of LLM decoding.

Weisi Yang, Zipeng Sun, Stephen Xia

Northwestern University · MILA – Quebec AI Institute · McGill University

Language Model Decoding LLM Inference Acceleration Autoregressive Decoding

Jun 25, 2026stat.ML

When are likely answers right? On Sequence Probability and Correctness in LLMs

Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token level or globally at the sequence level. Therefore, their success depends on a fundamental question: when does sequence probability, that is, the conditional probability of a continuation given a prompt, actually align with correctness? In this paper, we set out to quantify this relationship across decoding methods, models, and benchmarks at four levels: across decoding methods, across hyperparameters within a method, across prompt-answer pairs within a dataset, and across repeated responses to the same prompt. We find that higher sequence probability is often predictive of correctness across prompt-answer pairs within a fixed dataset. However, this relationship does not generally transfer to decoding decisions: increasing sequence probability by changing hyperparameters or methods does not reliably improve accuracy. Further, sequence probability is not a good indicator of correctness for responses to the same prompt. These findings clarify when decoding can and cannot be expected to improve correctness, and provide practical guidance for decoding, self-consistency, and verifier-free self-improvement.

Johannes Zenn, Jonas Geiping

Max Planck Institute for Intelligent Systems · ELLIS Institute Tübingen · AI Center Tübingen +2

LLM Evaluation Language Model Decoding LLM Reliability

Jun 22, 2026cs.LG

Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models

Masked diffusion language models decode by iteratively unmasking tokens, where the unmasking order defines an "order of thought" that strongly influences generation quality yet is typically chosen heuristically. We derive a tractable upper bound on the sequential decoding mismatch, measured by the Kullback-Leibler divergence and expressed in terms of the model's pathwise log-likelihood, with tightness under sufficient model expressivity. This bound induces a dense self-aware reward over ordered trajectories, casting order selection as a principled policy optimization problem with a frozen denoiser. We instantiate this idea as Self-Aware Scheduling (SAS), which learns a lightweight order policy using Group Relative Policy Optimization and applies seamlessly to both any-order and semi-autoregressive decoding. On Sudoku with 1B MDM, SAS improves puzzle accuracy from 82.0% (best heuristic schedule) to 91.8%, and reaches 97.5% with second-stage fine-tuning along learned trajectories. On mathematical reasoning with LLaDA-8B, SAS improves pass@1 on GSM8K from 64% to 76% and on MBPP from 39.5% to 41%, consistently matching or exceeding heuristic schedules across generation lengths and block sizes. Project page: https://jimmyxu123.github.io/SAS

Jiawei Xu, Minghui Liu, Aakriti Agrawal +2

University of Maryland, College Park · University of California, Los Angeles.

Masked Diffusion Models Language Model Decoding LLM Inference Scheduling Diffusion Language Model Decoding RL for Diffusion Models Diffusion Language Models+1

Jun 22, 2026cs.CL

The Anatomy of the CTC Oracle Gap: Acoustic Exhaustion and Linguistic Recovery

We study the limits of CTC-internal scoring for N-best hypothesis selection and locate the information bottleneck separating acoustic confidence from linguistic plausibility. Eleven CTC-internal and acoustic-feature scoring strategies produce no statistically significant WER improvement over greedy decoding on LibriSpeech dev-other at G=16 (all p > 0.05). The exhaustion is systematic: CTC's Spearman

ρ

between hypothesis score and per-utterance WER degrades from -0.574 at G=4 to -0.270 at G=128, a 53% loss driven by blank-path proliferation. This establishes that the discriminative capacity of CTC-internal representations is saturated: no recombination of acoustic signals can close the oracle gap. Confirming that the bottleneck is linguistic, not acoustic, external linguistic information introduced via MBR decoding breaks through it. MBR-CER decoding with a RoBERTa pseudo-log-likelihood (PLL) posterior (

τ

=10, G=128) achieves 5.42% WER on held-out LibriSpeech test-other (greedy 5.96%,

Δ

=-0.535 pp, p<0.0001, 9.0% relative). RoBERTa PLL

ρ

degrades only 21% over the same range, retaining discriminating power where CTC loses it. Applied without retuning across two Zipformer architectures, three domains (LibriSpeech, TED-LIUM 3, VoxPopuli), and four MUSAN noise levels, the recipe gives significant gains in 11 of 13 conditions. On the training side, standard MWER training via the CTC forward-backward algorithm implements Rao-Blackwellized REINFORCE at the output projection (variance about 3x below Viterbi). Yet sequence-level fine-tuning fails at near-converged checkpoints: all four MWER configurations on CR-CTC collapse (+6.18 to +8.90 pp WER), as a training oracle gap of 0.007 pp provides no usable reward signal.

Ivan Novosad

Faculty of Computer Science, HSE University, Moscow, Russia.

ASR Evaluation Language Model Decoding MBR Decoding

Jun 21, 2026cs.CL

Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding

In open-ended generation, LLMs frequently fall into the "likelihood trap", characterized by repetitive degeneration and vocabulary dullness, resulting in a discrepancy between machine-generated and human-written text. While post-hoc tail truncation (e.g., Top-p, Min-p) avoids sampling from the unreliable tail, it can misalign generation with human lexical preferences by over-sampling from the uncalibrated head; fixed scalar repetition penalties, in turn, ignore how the scale of the logit distribution varies across inference steps, which can disrupt semantic coherence. To address both shortcomings, we propose Variance-Calibrated Modulation (VCM), a training-free pre-decoding intervention. VCM directly reshapes the probability distribution prior to truncation via two dynamic mechanisms: (1) Contextual Searchlight via PMI, which naturally suppresses global stopwords and elevates context-evoked tokens, and (2) Adaptive Self-Debiasing, which utilizes real-time logit standard deviation to provide scale-invariant penalization. In experiments across open-ended generation, factual QA, and mathematical reasoning, we show that VCM consistently mitigates the likelihood trap. With negligible computational overhead, VCM integrates with existing decoding strategies, improving diversity and coherence and, particularly at higher decoding temperatures, reasoning accuracy. Our code is publicly available on GitHub: https://github.com/AetherDing/VCM

Yuanhao Ding, Meimingwei Li, Esteban Garces Arias +3

School of Computer and Information Engineering, Henan University · Department of Statistics, LMU Munich · 3Munich Center for Machine Learning (MCML)

Open-Ended Generation Language Model Decoding Text Generation

Jun 20, 2026cs.CL

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Autoregressive generation in large language models (LLMs) conventionally decodes from the final layer, assuming that deeper representations yield more reliable next-token predictions. We revisit this assumption by revealing a recurring Guess-Refine-Perturb dynamic: early layers form coarse guesses, intermediate layers refine reasoning-relevant semantics, and final layers can perturb these refined predictions toward generic or alignment-preferred tokens. We introduce Confident Decoding, a training-free decoding strategy that dynamically selects the most reliable near-final layer through entropy-guided conservative backward search. We further provide a theoretical formulation of layer selection as an optimal stopping problem, showing that under bounded projection noise and dominant late-stage alignment perturbation, our search rule filters perturbation while bounding the loss relative to the oracle refinement layer. Experiments across dense and Mixture-of-Experts LLMs demonstrate consistent gains on challenging reasoning benchmarks, including GPQA-Diamond, Omni-MATH, and HLE, with zero memory overhead and less than 2% latency increase. These results suggest dynamically bypassing final-layer perturbations can unlock stronger reasoning behavior from aligned LLMs.

Xuanming Zhang, Sining Zhoubian, Yuxuan Chen +8

Qwen Team, Alibaba Inc. · Tsinghua University · Nanyang Technological University

LLM Alignment Language Model Decoding Optimal Stopping LLM Reasoning

Jun 15, 2026cs.CL

From Awareness to Adherence: Bridging the Context Gap in Spoken Dialogue Systems via Context-Aware Decoding

Despite the success of end-to-end (E2E) spoken dialogue systems, maintaining strict context adherence in multi-round conversations remains a challenge. While prior works attribute these failures to models forgetting dialogue history, we highlight an equally critical but overlooked bottleneck: a gap between latent context awareness and active adherence. Although models internally recognize relevant past utterances, strong parametric priors often overshadow these signals during decoding. To bridge this gap, we propose an audio-adapted Context-Aware Decoding (CAD) approach. By leveraging internal attention mechanisms to isolate key historical rounds, our approach contrasts output distributions with and without this key context during inference, directly amplifying multimodal contextual signals. Evaluations on the Audio MultiChallenge benchmark demonstrate significant improvements in Semantic Memory and Self Coherence subtasks, successfully enforcing strict, context-faithful adherence.

Che Hyun Lee, Heeseung Kim, Sungroh Yoon

ECE and 2 IPAI, Seoul National University, Seoul 08826, Korea · Department of AI, University of Seoul, Seoul 02504, Korea

Language Model Decoding Spoken Dialogue Systems

Jun 15, 2026cs.CL

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead. Latent reasoning offers a promising alternative by carrying part of the computation in continuous representations. However, existing methods typically predefine when latent computation is invoked and how it is allocated during decoding, leaving a key problem unresolved: when to invoke latent computation, what type of computation to perform, and how much budget to allocate. We propose \textbf{Ty}ped \textbf{L}at\textbf{e}nt \textbf{R}easoning (Tyler), a typed and budget-aware framework for latent reasoning during autoregressive decoding. Tyler learns a policy that, at each decoding step, chooses between emitting a text token and switching to a latent computation module specialized for a particular reasoning function. Once invoked, an operator maps the current reasoning state into latent tokens that support global planning, local state updates, or reusable procedural abstraction. Across extensive experiments on three backbone LLMs, Tyler improves accuracy by up to 14.49 points over CoT and by up to 4.30 points over the strongest competing baseline. It further generalizes across diverse reasoning domains and achieves the best final-stage performance with the lowest forgetting.

Hanyu Lin, Min Cai, Jiawei Wen +1

1Shenzhen University · University of Alberta

Language Model Decoding Efficient Language Model Reasoning Continuous Latent Reasoning LLM Reasoning Adaptive Computation Latent Reasoning

Jun 12, 2026stat.ML

Adaptive Nucleus Truncation for Long-Form Reasoning

Sampling plays an important role in long-form language-model reasoning. Over thousands of decoding steps, small changes in the candidate token set can compound into different reasoning trajectories, stability profiles, and final answers. Existing truncation methods such as top-

p

, min-

p

, and fixed top-

nσ

sampling improve over unrestricted sampling, but they rely on fixed thresholds that cannot adapt to changes in entropy, task difficulty, training stage, or generation budget. We introduce Adaptive Nucleus Truncation Sampling (ANTS), which extends top-

nσ

sampling from a fixed decoding rule into an adaptive rollout-control mechanism for long-form generation. ANTS selects standardized neighborhoods around the maximum logit before temperature scaling, adapts the truncation width using an entropy-conditioned controller, and retains a no-truncation fallback arm to stabilize training when truncation becomes unsafe. On a 33B-total / 4B-active sparse Mixture-of-Experts reasoning model, ANTS improves average performance over percentage-based benchmarks by +1.9, +3.8, and +5.2 points at 8K, 16K, and 32K generation budgets, respectively. The strongest gains appear on instruction following and mathematical reasoning, with IFBench improving by more than 10 points at 32K and AIME 2025 improving by 7 points. Code generation reveals an important budget interaction. On Codeforces, ANTS trails the baseline at 8K, but reverses this gap and substantially improves ELO at 16K and 32K. These results suggest that sampler design should be treated not just as a decoding hyperparameter, but as part of how we stabilize and scale long-budget reasoning.

Ousmane Amadou Dia

Language Model Decoding Adaptive Sampling LLM Reasoning Large Reasoning Models

Jun 11, 2026cs.LG

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on token-level uncertainty during reasoning. We show that quantization increases incorrect sampling at low-entropy symbolic tokens, while causing over-concentration on a small set of tokens in high-uncertainty reasoning steps. Based on this observation, we propose \textbf{ReSET}, a reasoning-step entropy-based temperature-scaling method that estimates step-level uncertainty online and adapts the decoding temperature using both token-level and step-level entropy signals. To address the latency gap, we further design a CUDA-core small-

M

NVFP4 kernel for latency-critical autoregressive decoding. Across reasoning benchmarks and model scales, ReSET improves NVFP4 reasoning accuracy by up to

\sim\!

2 points over the NVFP4 baseline. Our CUDA-core small-

M

kernel further improves latency-critical decoding, delivering up to

2.5\!\times

kernel-level speedup over NVFP4 vLLM and approximately

2\!\times

end-to-end decoding speedup over BF16. Code is available at https://github.com/aiha-lab/ReSET.

Sihwa Lee, Janghwan Lee, Donghoon Yoo +4

Hanyang University, Seoul, Republic of Korea · Xenoscube Korean Inc., Seoul, Republic of Korea

LLM Quantization Language Model Decoding GPU Kernel Optimization LLM Inference Acceleration Large Reasoning Models

Jun 10, 2026cs.CL

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

Decoding-time truthfulness methods -- layer-contrast decoding, inference-time intervention, and learned logit adapters -- have demonstrated 10-30 point gains on TruthfulQA when applied to base language models. However, modern instruction-tuned LLMs already achieve substantially higher baselines (61-76%), raising the question of whether these methods remain effective in practice. We design a six-control evaluation framework -- out-of-distribution training, multi-judge validation, simple decoding baselines, confound controls, bootstrap confidence intervals, and seed variance -- and apply it across 5 models (1B-70B), 3 benchmarks, and 15 methods. We find that previously reported gains shrink substantially under strict controls: on the full TruthfulQA benchmark (N=817), no token-level method achieves statistically significant improvement, and the best learned adapter scores -2.0 points below greedy (p=.23). We identify five evaluation sensitivities -- contamination, judge choice, missing baselines, confounds, and statistical noise -- that individually or jointly account for these discrepancies. Cross-benchmark validation on HaluEval QA and TriviaQA confirms that these patterns extend beyond TruthfulQA. Deliberative prompting methods (chain-of-thought, self-critique) appear more robust in the evaluated regime, with CoT achieving +5.6-19pp across benchmarks as a training-free, single-pass method. We release a seven-point evaluation checklist and discuss implications for future truthfulness research.

Ao Sun

Independent Researcher

LLM Evaluation Language Model Decoding Question Answering

Jun 9, 2026cs.LG

CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference

Large language model inference is bottlenecked by autoregressive decoding, where each token requires a full forward pass. Multi-token prediction (MTP) offers a promising acceleration path, but existing approaches suffer from a fundamental architectural flaw: the MTP head for the first token competes with the backbone's own language model (LM) head, leading to severe quality degradation when predictions are accepted. We identify this head-backbone competition as the root cause of repetitive and incoherent outputs in prior MTP-based acceleration methods. To address this, we propose Backbone-as-Architect, a design principle where the backbone LM head always generates the first token, and MTP heads are responsible only for subsequent tokens. Building on this principle, we introduce CLP (Collocation-Length Predictor), a lightweight span-level decision layer that predicts how many additional tokens can be safely accepted at each decoding step. CLP uses only a single linear layer (4.6K--7.7K parameters), replacing the over-engineered 1M-parameter gate networks used in prior work. Experiments on Qwen2.5 models (0.5B, 1.5B, 7B) show that CLP achieves 1.20x--1.29x speedup on 1.5B and 1.14x--1.20x on 7B, with zero quality degradation (repetition ratio < 0.02), while gate-based approaches fail to accelerate (1.07x) or produce severely degraded outputs (repetition ratio > 0.5%). We further demonstrate that shorter prediction horizons (k=2) recover 24% higher MTP head accuracy on large models, establishing a scaling-aware design principle. We identify MTP head prediction accuracy as the binding constraint on acceleration and establish a clear roadmap for future improvements.

Xuezhen Xie, Zhiqiang Zhou

Multi-Token Prediction Language Model Decoding Next-Token Prediction LLM Inference Acceleration

Jun 9, 2026cs.LG

K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling

Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mapping--one that transforms independent uniform noise variables into a joint sample of multiple future tokens in a single forward pass. This design preserves fixed-length outputs, reuses the AR teacher backbone, and remains compatible with standard AR serving infrastructure. We train this mapping via progressive self-forcing distillation, which gradually expands the prediction window while enabling the student to closely match the sequence distribution of the AR teacher. We evaluate K-Forcing on LM1B and OpenWebText using a standard causal Transformer backbone. When aggressively configured to generate k = 4 tokens per forward pass, K-Forcing delivers approximately 2.4-3.5x speedup across different batch sizes, while incurring modest quality degradation relative to its AR teacher. As inference increasingly dominates the lifetime compute cost of modern LLMs, K-Forcing offers a promising route toward accelerating AR generation under real-world high-load deployment.

Zhiwei Tang, Yuanyu He, Yizheng Han +4

1DAMO Academy, Alibaba Group · 2Hupan Lab · 3Zhejiang University +1

LLM Serving Language Model Decoding Autoregressive Language Modeling LLM Inference Acceleration Language Model Distillation

Jun 9, 2026cs.IR

STORM: Stepwise Token Optimization with Reward-Guided Beam Search

Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever the model changes. Lexical retrievers like BM25 stay efficient and transparent on a standard inverted index that need not change as models evolve, but suffer from vocabulary mismatch. LLM query rewriting can help, yet prompted rewriters emit well-formed but retrieval-ineffective or harmful-terms, and training against a retrieval reward gives only delayed, sequence-level supervision that obscures which terms helped. We introduce STORM (Stepwise Token Optimization with Reward-guided beaM search), a self-supervised framework for lexical query expansion. STORM trains the rewriter through generation guided by retrieval metrics: at each step, candidate expansions are scored against the BM25 index and low-reward continuations pruned, turning the retrieval reward into a token-level signal that concentrates exploration on retrieval-effective vocabulary. Across TREC DL and BEIR, STORM lets 0.6B-8B backbones match or surpass competitive LLM rewriters while retrieving as fast as plain BM25; at 8B it rivals far larger proprietary rewriters. It further transfers zero-shot to 18 languages (MIRACL), beating dedicated multilingual dense retrievers on average, making STORM a competitive, infrastructure-light alternative to dense neural retrieval.

Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong +3

MILA – Quebec AI Institute & ILLS, Canada · 5Sapienza, University of Rome, Italy · 4Sorbonne Université & ISIR & CNRS, France +2

Language Model Decoding Lexical Retrieval Information Retrieval Query Expansion

Jun 8, 2026cs.CL

Gradient-Guided Reward Optimization for Inference-time Alignment

Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation. While inference-time alignment methods such as Best-of-

N

and rejection sampling are widely used, they frame the task as a sampling-intensive, reward-guided search, leading to two key limitations: their performance is bounded by the base model's generation quality, and their reliance on imperfect reward models makes them vulnerable to reward hacking. To address these challenges, we introduce Gradient-Guided Reward Optimization (GGRO), a lightweight inference-time method that performs targeted, minimal intervention during decoding via gradient guidance. Specifically, GGRO monitors token-level entropy to identify high-uncertainty regions indicative of drift or misalignment. Upon detection, it responds by injecting nudging tokens, generated using gradient signals from an off-the-shelf reward model, to steer the generation trajectory rather than merely re-ranking samples. Experiments show that GGRO consistently improves inference-time alignment across safety, helpfulness, and reasoning benchmarks. It also increases coverage of high-quality responses and robustness to reward hacking, with minimal computational overhead. Code is available at https://github.com/lhk2004/GGRO.

Hankun Lin, Ruqi Zhang

Department of Computer Science, Purdue University

Reward Hacking LLM Alignment Language Model Decoding Inference-Time Language Model Alignment Inference-Time Guidance

Jun 8, 2026cs.CR

Steganography Without Modification: Hidden Communication via LLM Seeds

We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generators (PRNGs) used in inverse-transform sampling produce a seed-dependent sequence of token-level probability intervals that can be reconstructed from the generated text alone. A sender encodes a secret message in the PRNG seed before generation; a receiver reconstructs the intervals and recovers the seed, and thus the hidden payload, by exhaustive search over the seed space. We formalize two operational modes. In the known-prompt setting, sender and receiver share the prompt, enabling exact interval reconstruction and perfect seed recovery via forced alignment. In the unknown-prompt setting, only the generated text is available; approximate interval reconstruction combined with a maximum-hit-count scoring strategy still permits reliable recovery from sufficiently long outputs. Extensive experiments across six model families and five heterogeneous text domains show that, in the known-prompt setting, full 32-bit seed recovery from the complete 2^32 candidate space achieves up to 100% accuracy, depending on model and text domain, within 300 tokens and under 35 seconds on a single GPU. In the unknown-prompt setting, recovery reaches near-perfect accuracy at 600-800 tokens in about 12 seconds. We further analyze the influence of prompting strategies, tokenization ambiguities, and sampling hyperparameters on channel reliability. Moreover, we discuss several applications of our results: First, it allows for the steganographic transmission of 32 bits, but also shows that ignorance of the prompt is not a valid security assumption.

Felix Mächtle, Jonas Sander, Sebastian Berndt +3

Institute for IT Security, University of Lübeck, Lübeck, Germany · Technische Hochschule Lübeck, Lübeck, Germany

Language Model Decoding LLM Inference LLM Security

Jun 8, 2026cs.AI

The Token Not Taken: Sampling, State, and the Stochasticity of AI Agents

Agentic AI systems can behave differently across runs: the same request may produce a different plan, a different tool call, a different code edit, or a different final answer. Such variability arises from several layers that are often conflated. At the core of many current agents is a foundation model, a large pretrained model adaptable to many downstream tasks, embedded in an orchestration loop that plans, calls tools, observes results, and updates state. One explicit intrinsic source of variability in such systems is token generation: the model computes scores over possible next tokens, the scores are converted into probabilities, and a decoder may sample tokens using a pseudo-random number generator. A small sampled token difference can then cascade downstream into a different tool call, code path, search query, or agent state. Other sources of variability are extrinsic to token sampling, including changing environments, live data, serving infrastructure, batch effects, and numerical details. By separating these layers, this tutorial clarifies what it means to call agentic AI systems stochastic, when such variability can be reproduced under matched conditions, and why deterministic execution need not imply identical behavior in deployed settings.

Muhammad Zia Hydari, Raja Iqbal

University of Pittsburgh · Ejento AI Inc.

Language Model Decoding LLM Agents LLM Agent Reliability

Jun 7, 2026cs.CL

Inside the LLM Word Factory

Transformer language models process input provided as subword fragments, but natural language semantics usually rely on word-level concepts. Detokenization is the process where models reconcile these two facts, aggregating subwords into word-level representations through their computation. Prior work has found that this takes place mostly in early-to-middle layers, but so far the exact mechanics of the process have not been pinned down. We venture deep into detokenization using activation patching in controlled paired experiments that isolate the contribution of different model components, localizing English detokenization in Llama2-7B to a two-stage process at Layer 1. Attention transmits a token-specific signal from nonfinal subwords, using sequential relays if necessary, while the MLP composes it with the local embedding. This two-stage structure generalizes to twelve models from eight families, but the depth over which it takes place depends on the flavor of positional encoding: RoPE-based models detokenize over 1 to 5 layers, while learned-absolute models take 5 to 10. Finally, we provide a probe for determining the success of the detokenization process based on early-layer activations alone, performing at 0.94-0.97 AUROC depending on the amount of context.

Benzi Busigin, Yuval Pinter

Stein Faculty of Computer and Information Science Ben-Gurion University of the Negev Beer Sheva, Israel

Language Model Decoding LLM Interpretability Subword Tokenization

Jun 5, 2026cs.CV

Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding

Online Video Large Language Models (Video-LLMs) have advanced toward seamless human-AI interaction through frame-by-frame processing and proactive responding. However, a critical challenge remains in streaming scenarios: existing models typically pause video perception while generating responses, breaking real-time video-language synchrony and causing stutters. To address this, we introduce a novel paradigm for online video understanding: Streaming Video-Language Synchrony (SVLS), and present LyraV, a live streaming assistant built upon a hierarchical control framework with two core innovations. First, the Frame-Driven Transition Controller (FDTC), a training-free verification-based finite-state machine, makes high-level semantic decisions on when to continue speaking, start a new response, or stay silent. Second, the Streaming Token Pacer (SToP), a plug-and-play lightweight predictive module, dynamically adapts the language generation rate to match the pace of the visual content. Concretely, LyraV performs \emph{per-frame incremental, sub-budget decoding}: within each frame interval it emits only a small chunk of tokens that fits the real-time budget, so perception is never blocked for a full sentence. Together, these components enable LyraV to seamlessly interleave incoming video frames with generated word tokens, achieving a fine-grained synchrony. Extensive experiments conducted on five online and three offline benchmarks demonstrate that LyraV preserves the backbone's general understanding ability while substantially improving streaming synchrony and narrative fluency, delivering a 98.29% synchrony with video playback and a real-time processing speed of 3.89 FPS. Interestingly, we observe an empirical capability in LyraV: dynamic reasoning over streaming tokens, enabling continuous interpretation and "thinking" alongside visual input.

Zhenyu Yang, Kairui Zhang, Shengsheng Qian +2

Streaming Video Understanding Language Model Decoding VLM Inference