LLM Fine-Tuning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

42 papers in the last four weeks, up 83% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 509

Sep 29, 2026cs.CL

Compiling Learning Problems into Adaptation Programs for Language Models

Model adaptation is typically governed by a fixed recipe, even though different update programs can produce substantially different behavioral outcomes. We introduce adaptation compilation, which reframes where, how, and to what extent a model should adapt as a joint prediction and decision problem. Rather than searching over candidate programs anew for each learning episode, a compiler learns from prior adaptations to predict a vector-valued counterfactual response surface over candidate programs---their expected effects on acquisition, transfer, boundedness, and preservation---and selects a program before adaptation begins. Because this predicted geometry captures multiple behavioral consequences rather than a single winner or scalar score, it can be reused under different downstream priorities without retraining. Across five learning types, preferred programs vary meaningfully across episodes, and this variation is predictable from pre-adaptation information. On Llama-3.1-8B, compiler-selected programs approach exhaustive search while outperforming global and objective-specific defaults. Replication on Gemma-2-9B preserves program heterogeneity and selection headroom, but shows that exploiting this headroom requires accounting for uncertainty when departing from strong defaults. Together, these results show that adaptation search can be amortized across related learning problems, turning prior adaptation experience into a basis for deciding how future learning should occur.

Rebecca Ramnauth, Brian Scassellati

Department of Computer Science Yale University New Haven, CT 06511, USA

Meta-Learning LLM Fine-Tuning

Sep 29, 2026cs.CL

VLM Fine-Tuning for End-to-End Combinatorial Optimization

Large language models (LLMs) have provided a unified interface for end-to-end combinatorial optimization (CO), but textual serialization alone may obscure spatial and relational structures that are important for generating effective CO solutions. This paper presents a general-purpose vision-language solver that augments textual instance descriptions with input-derived visual representations. A single vision-language model (VLM) is applied across different CO tasks and trained using supervised fine-tuning followed by verifier-guided reinforcement learning. While the visual inputs contain no gold solutions or solution-derived information, our experiments show that the VLM generally improves solution quality over its text-only counterpart, with particularly clear gains on more complex CO problems such as CVRP and JSSP. The advantage of visual information is more pronounced at large problem scales.

Qingsong Yan, Xia Jiang, Yaoxin Wu +3

College of Computer Science, Sichuan University · Department of Industrial Engineering&Innovation Sciences, Eindhoven University of Technology · Institute of Marine Science and Technology, Shandong University +1

LLM Fine-Tuning Neural Combinatorial Optimization

Sep 29, 2026cs.AI

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A task-trained rank-8 LoRA at one early layer extends this computation with all model weights frozen. Qwen3-8B improves from 15.5% to 99% exact accuracy on 24-line chains; a longer-trained LoRA reaches 50 lines. Ouro-1.4B reaches 60 lines after four loops and at least 160 after eight. The LoRA starts a relay: program lines pass on their chain identity through a short range of middle layers. Frozen heads read progressively further up the chain, and removing parent-line attention stops the relay. A frozen-model measurement locates the last useful intervention layer within tolerance in three of four held-out models. Task-specific LoRAs also improve MuSiQue. Default answers therefore understate the computation accessible through a tiny edit. Code and an interactive demo are available at https://lunamos.github.io/stop-thinking-too-early/

Zehao Jin, Ruixuan Deng, Junran Wang

Georgia Institute of Technology

Transformer LLM Fine-Tuning Low-Rank Adaptation Causal Interventions in Language Models LLM Reasoning

Sep 28, 2026cs.CL

Population Fidelity: Evaluating Population Representativeness in LLMs

Large language models (LLMs) show considerable potential in simulating human attitudes and preferences. Prior work finds that LLM-generated responses can compress the range of attitudes found within populations and misrepresent particular subgroups in ways that vary across models and topics. We introduce Population Fidelity, an evaluation framework that distinguishes key conditions required for a set of LLM-generated responses to represent a population. It incorporates three dimensions: group-level accuracy, the amount of between-group variation, and the structure of that variation. We demonstrate the framework's utility in two ways. First, we reproduce a prior study of "machine bias" in LLM survey responses and apply the framework to its models and more recent ones, showing that poor representation reflects not only insufficient between-group variation but also variation assigned to the wrong groups. Second, we evaluate one proposed approach to improving models' population representativeness: cultural fine-tuning. We find that cultural fine-tuning can improve alignment with the survey center without improving the representation of within-population differences, a distinction that measures of aggregate agreement do not capture. We argue that representing a population requires models to reproduce several features of human attitudinal variation simultaneously. Our framework organizes these features and provides reusable code, data, and trained models for evaluating population fidelity across substantive domains and assessing proposed alignment methods.

Neemias B. da Silva, Martin Lukk, Ali Sutani +5

University of Toronto, Canada · Federal University of Technology – Paran´a, Brazil

LLM Evaluation LLM Fine-Tuning Large Language Model-Based Social Simulation Demographic Bias in Language Models

Sep 28, 2026cs.LG

AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning

Zeroth-order (ZO) optimization offers a memory-efficient alternative for LLM fine-tuning by estimating updates only from forward evaluations of perturbed parameters, without backpropagation or activation storage. However, in billion-parameter LLMs, isotropic perturbations often waste many forward evaluations on weakly informative directions. To make these evaluations more informative, existing ZO methods restrict perturbations to low-dimensional subspaces. Yet the quality of these subspaces is critical: overly compressed or poorly maintained spaces can miss useful update directions. To obtain a high-quality subspace for ZO updates, this paper proposes AIM-ZO, a ZO fine-tuning method based on Activation-Informed Subspace Maintenance. AIM-ZO uses forward activations as local directional information and continuously integrates them into a broad, evolving subspace over training. To access broader gradient-relevant structure while keeping individual perturbations low-dimensional, AIM-ZO activates only a smaller set of shared and sampled directions, decoupling the maintained width from the active width. We evaluate AIM-ZO across 5 LLMs and 11 downstream tasks under matched forward-evaluation budgets; its six-task average exceeds the strongest fully evaluated ZO baseline by 1.26 percentage points on OPT-2.7B and MeZO by 2.85 percentage points on OPT-30B. Our code is available at https://github.com/EkkoXy/AIM-ZO

Yue Xie, Zhi Zheng, Yunpeng Ba +5

Southern University of Science and Technology · National University of Singapore · Huawei Technologies Ltd. +1

Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning

Sep 27, 2026cs.AI

How code helps different tasks? A decompositional lens on LLM post-training

Evaluating code data as a single corpus can obscure which types of code data benefit which models and downstream tasks. Effective data selection requires understanding both the benefits of individual categories and whether these benefits persist when categories are combined. We introduce a decompositional lens for studying these effects in LLM post-training. We first decompose an execution-verified code corpus into interpretable categories based on the computational patterns of its solutions. Through controlled fine-tuning experiments, we compare individual categories with a balanced mixture across instruction-tuned models on question answering, mathematics, and code generation. The resulting response maps reveal recurring gains in average question-answering performance, while the same category can improve one model or task and degrade another. The best-performing category also varies with the starting model and target task. We then compose compact mixtures guided by these results and examine whether benefits observed in individual categories persist under joint training. On selected model--task pairs, mixtures whose constituents each improve the target task outperform both their best constituent and full-corpus training while using roughly 10--15% of the full corpus. These exploratory findings illustrate a \emph{less is more} pattern and highlight how the value of code data in post training depends on which categories are combined for which model and task.

Zheng Yu, Yiwei Li, Yishen Chen +4

Sun Yat-sen University · Shenzhen Loop Area Institute · The Chinese University of Hong Kong, Shenzhen +1

LLM Fine-Tuning Instruction-Tuning Data Selection Training Data Selection LLM Post-Training LLM Code Generation LLM Reasoning

Sep 24, 2026cs.LG

Beyond Average Safety: Chance-Constrained LLM Fine-tuning

Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-critical prompts. Existing safety-preserving fine-tuning methods typically control average safety loss or use weighted auxiliary penalties, which can obscure rare but severe failures. We propose a chance-constrained formulation for safety-preserving fine-tuning that limits the fraction of safety examples whose degradation relative to a reference model exceeds a prescribed threshold. Because the resulting empirical chance constraint contains a discontinuous indicator, we introduce a differentiable majorization of the violation rate, yielding a tractable conservative constraint. We then develop a constraint-aware gradient descent method that treats the majorized constraint as a safe set in parameter space and minimally modifies the fine-tuning direction to preserve feasibility. The resulting update admits a closed form and produces a tail-aware safety correction that emphasizes examples near or above the degradation threshold. We conduct an extensive set of experiments on harmful fine-tuning across three different tasks and three models and show that our approach consistently outperforms the baselines that exist in the literature. These results suggest that safety preservation in LLM fine-tuning is better viewed as a reliability-constrained optimization problem than as average-risk regularization.

Taha Entesari, Mahyar Fazlyab

Department of Electrical and Computer Engineering Johns Hopkins University

Stochastic Optimization Chance-Constrained Optimization LLM Fine-Tuning LLM Reliability LLM Safety

Sep 24, 2026cs.CL

Rufus-Air: An Open LLM Post-Training Recipe

Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge-based signals. Training builds on open-source components and public data, much of it used as released, without new human annotation or an in-house distillation teacher. Our main findings are that (i) diverse, high-quality SFT establishes a strong capability floor; (ii) difficulty filtering keeps RL prompts within a productive learning range; (iii) reward reliability provides a practical principle for ordering stages; and (iv) infrastructure and engineering choices are part of the recipe, not just an implementation detail. Rufus-Air improves over the official GLM-4.5-Air post-trained release and is competitive with similarly sized open models.

Chia-Yuan Chang, Renyuan Cheng, Rui Feng +19

Amazon

LLM Fine-Tuning RL for Language Model Reasoning RL Post-Training LLM Post-Training RL for LLM Agents

Sep 23, 2026cs.IR

The Fellowship of the Query: Learning Retrieval Actions

Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify progress, and stop. We study whether trajectory fine-tuning can improve small language models (SLMs) as next-action controllers. We additionally evaluate a low-resource setting in which a single SLM serves as both the controller and the final-answer generator. From accepted teacher search traces, we build a seven-way action-prediction task, where the model predicts the next structured teacher action from the current trajectory state, and evaluate LoRA-supervised fine-tuning across SLMs and xSLMs as controllers. On 1,646 held-out action examples, Granite 4.1 3B trained on 13,194 actions reaches macro-F1 0.6536, compared with 0.1736 for zero-shot prompting of the same model and 0.5399 for a TF-IDF logistic-regression baseline. In an end-to-end controller/generator swap evaluation over 149 held-out trajectories, using the fine-tuned model for both roles improves Exact Match from 0.7530 to 0.7946 and token F1 from 0.7783 to 0.8295 compared with using the base model as both controller and generator. The cross-role conditions show that the fine-tuned controller increases evidence-fact recording when the generator is fixed, while controller-only final-answer gains are not statistically clear. Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline. Code is available at https://github.com/padas-lab-de/agent-action-controller

Mohammed Al-Maamari, Saber Zerhoudi, Michael Granitzer +1

University of Passau Passau, Germany

LLM Fine-Tuning Agentic RAG LLM Agent Training

Sep 23, 2026cs.CL

Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

Fine-tuning large language models on parallel data improves translation quality but can cause catastrophic forgetting. Mitigation methods are generally evaluated by retention on general benchmarks. We ask whether these findings transfer to machine translation (MT) fine-tuning and to MT-specific instruction following (MT-IF): instructions that modify a translation, such as formality, grammatical gender, and length control. We compare methods anchored to auxiliary data, to model outputs, and to the base model parameters, first in a screening study with Llama 3.2 1B Instruct, then on Llama 3.1 8B Instruct fine-tuned on bidirectional Arabic-English or Spanish-English data. Elastic Weight Consolidation preserves general capabilities best in both stages; on the 8B Spanish model the average score on general benchmarks drops 1.7 points versus 11.0 for standard fine-tuning, yet its scores for formality and grammatical gender control remain close to standard fine-tuning. Only data mixing with control-task examples preserves these controls, but its gains do not transfer to unseen prompts for the same task.

Niklas Scholz, David Thulke, Abdallah Nasir +3

AppTek GmbH, Aachen, Germany · Machine Learning and Human Language Technology, RWTH Aachen University, Germany · Applied Science Private University, Amman, Jordan

LLM Fine-Tuning Elastic Weight Consolidation Machine Translation Catastrophic Forgetting

Sep 23, 2026cs.CL

Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs

Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or tool-use decisions. A central deployment question is whether these skills should be handled by separate task-specialist models or by a single model trained through multi-task training, sequential updates, or model merging. We study this question using thirteen models spanning five families (Qwen3, Qwen3.5, Gemma-3, Llama-3.1, and Mistral) from 0.6B to 32B parameters across eight customer-support datasets, spanning four public and four proprietary datasets with approximately 74.5k training and 8.7k evaluation samples. Under a fixed training protocol, we train more than 200 checkpoints. Our experiments reveal that multi-task full fine-tuning is the strongest operational default at every model size we test. Specialist models are strong on their target tasks but often degrade sharply off-task, making reliable routing important. Sequential Low-Rank Adaptation (LoRA) preserves earlier skills better than sequential full fine-tuning, while merging a specialist with its base model improves off-task robustness with limited same-task loss for larger models. We conclude with practical guidelines for selecting fine-tuning strategies in real-world settings.

Md Tahmid Rahman Laskar, Xue-Yong Fu, Shashi Bhushan TN

Dialpad Inc.

Fine-Tuning Customer Support Automation LLM Fine-Tuning Language Model Merging Parameter-Efficient Fine-Tuning

Sep 23, 2026cs.LG

Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders

Next-token prediction has enabled highly fluent autoregressive language models, but it represents global structure only indirectly through sequential factorization. In contrast, high-fidelity autoencoders have become a standard primitive in image generation, enabling generative models to operate over continuous latent spaces; text lacks a comparably faithful continuous representation. We propose LLMAE, a method for repurposing a pretrained decoder-only language model as a continuous text autoencoder by exposing an intermediate fixed-length latent bottleneck within its internal activations. Instantiated with a parameter-efficient 270M Gemma 3 model, LLMAE uses structured attention masks, LoRA adaptation, and KL regularization to learn an autoencoding interface that leverages the generative prior of the original LLM. We train LLMAE to reconstruct text sequences up to 1024 tokens, significantly improving on this task to achieve near-perfect reconstruction. Furthermore, we demonstrate the downstream utility of this representation by training a latent text diffusion model for detailed image captioning using the learned LLMAE autoencoder. By mapping text into a fixed-length continuous latent space, our approach provides an effective substrate for downstream adaptation while benefiting from the fluency of the original LLM.

Arkanath Pathak, Unnat Jain, Alexander C. Berg

University of California, Irvine

Decoder-Only Language Models Autoencoders LLM Fine-Tuning

Sep 22, 2026cs.AI

Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA

Reinforcement learning (RL)-based post-training has become an effective approach for eliciting reasoning capabilities in large language models (LLMs). However, adapting post-RL models to new knowledge domains or behaviors through subsequent supervised fine-tuning (SFT) can severely overwrite these capabilities. Existing approaches mitigate such forgetting through experience replay, specialized initialization, or constrained optimization using gradient projection, but either provide limited preservation or incur substantial training overhead. Our analysis shows that reasoning activations concentrate in low-dimensional subspaces, leaving substantial null-space capacity for adaptation, and that the corresponding approximate null spaces can be reliably estimated from a modest number of examples. Motivated by these observations, we propose Null-Basis Low-Rank Adaptation (NB-LoRA), a parameter-efficient method for adapting post-RL LLMs while preserving their acquired reasoning ability. We formulate reasoning retention as a layer-wise hidden-state preservation constraint and construct a fixed approximate null basis from reasoning activations. LoRA updates are then reparameterized through this basis, enforcing the preservation constraint throughout fine-tuning. Extensive experiments across multiple RL-trained LLMs and diverse downstream tasks show that NB-LoRA matches standard LoRA in adaptation performance, maintains reasoning accuracy near pre-fine-tuning levels, and generalizes this preservation to held-out reasoning benchmarks.

Wenzhi Fang, Nicholas Tzou, Lazar Valkov +1

Samsung Research America, Mountain View, CA, USA · Purdue University, West Lafayette, IN, USA

LLM Fine-Tuning Low-Rank Adaptation RL Post-Training

Sep 21, 2026quant-ph

Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models

Language models can be adapted by changing the computations applied to individual tokens. Quantum circuits offer one such approach, but evaluating wider circuits inside a large model can be computationally demanding. Here we introduce HyperQ, which adds token-conditioned quantum residual branches to a frozen masked-diffusion language model. A quantum residual branch is a module in each transformer block that reads a token's hidden state, emits the coordinates of that token's circuit, executes it, and adds the measured values back through a residual connection. The backbone remains frozen, and only the added branches are trained. Within each branch, a lightweight circuit hypernetwork emits token-specific rotation angles, coupling strengths, and measurement axes in a shared sparse circuit structure. The required expectation values have an exact classical expression whose evaluation cost grows linearly with the qubit count, enabling circuits from 16 to 64 qubits to be trained within a 1.1-billion-parameter backbone. Across downstream benchmarks, increasing circuit width raises the average score from 47.65 to 54.30. At 64 qubits, HyperQ exceeds the backbone and its low-rank-adapted counterpart by 4.71 and 3.67 points, respectively. HyperQ is fine-tuned on 20,000 prompt-response pairs, compared with 200,000 for the classical baselines. These findings support token-conditioned circuit emission as a tractable architectural approach to quantum-augmented language modelling.

Xiaoqiang Wang, Mengyang Xiong, Jun Dai +1

D´epartement d´informatique et de recherche op´erationnelle, Universit´e de Montr´eal, Montr´eal, QC, Canada. · Mila, Quebec AI Institute, Montr´eal, QC, Canada. · McGill University, Montr´eal, QC, Canada.

LLM Fine-Tuning Quantum Machine Learning Circuits in Language Models Diffusion Language Models

Sep 21, 2026cs.CL

QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation

Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.

Demian Pavlyshenko, Bohdan Pavlyshenko

LLM Fine-Tuning LLM-Assisted Annotation

Sep 16, 2026cs.CL

SEA-LION-v4.8: A Technical Report

We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages In One Network (SEA-LION) models built upon NVIDIA Nemotron 3. The family includes 30B-A3B and 120B-A12B models, with both continued-pretrained base checkpoints and post-trained variants. We adapt the models using Southeast Asian, reasoning, code, and multilingual parallel data, followed by post-training with supervised fine-tuning and online on-policy distillation. On SEA-HELM, the 30B-A3B model improves the overall SEA score from 46.06 to 51.57, while the 120B-A12B model improves from 49.30 to 63.44. Across seven Southeast Asian languages, we observe broad capability gains with the 120B-A12B model showing broader and more consistent improvements across tasks.

Ahmed Mohammad Dabeer, Ahn Jeongmi, Anocha Sutaveephamochanon +45

David Wang Dawei · Li Chunren · Huang Wenzong, Raymond +1

Multilingual Language Models LLM Fine-Tuning

Sep 15, 2026cs.CL

Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation

This paper addresses the challenge of making complex healthcare information more accessible through automated Plain Language Adaptation (PLA). PLA aims to simplify technical medical language, bridging a critical gap between the complexity of healthcare texts and patients' reading comprehension. Recent advances in Large Language Models (LLMs), such as GPT and BART, have opened new possibilities for PLA, especially in zero-shot and few-shot learning contexts where task-specific data is limited. In this work, we leverage the capabilities of LLMs such as GPT-4o-mini, Gemini-1.5-pro, and LLaMA for text simplification. Additionally, we incorporate Mixture-of-Agents (MoA) techniques to enhance adaptability and robustness in PLA tasks. Key contributions include a comparative analysis of prompting strategies, finetuning with QLoRA on different LLMs, and the integration of MoA technique. Our findings demonstrate the effectiveness of LLM-driven PLA, showcasing its potential in making healthcare information more comprehensible while preserving essential content.

Ting-Wei Chang, Hen-Hsen Huang, Hsin-Hsi Chen

Department of Computer Science and Information Engineering, National Taiwan University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · AI Research Center (AINTU), National Taiwan University, Taiwan

LLM Fine-Tuning

Sep 15, 2026cs.CL

Where Should a Document Live: Context, Representations, or Parameters?

To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive benchmarks. We show that in the oracle setting, Cartridges (KV) are the most accurate injection method at nearly every storage budget, outperforming parametric methods by 10 points. Compaction (KV) matches Cartridges only at low compression rates, lagging behind the parametric methods by 10 points at rates higher than

50\times

. In the more realistic multi-document retrieval scenario, Cartridges are the only method that matches in-context learning (ICL), leading the parametric methods by 29 points and Compaction by 15 points. Nonetheless, Cartridges are also the only method, besides full fine-tuning and large MLP adapters, that suffers from catastrophic forgetting, i.e., a 6% performance degradation on control benchmarks, with 13% in coding.

Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias +1

Amazon AGI

Memory-Augmented Language Models Knowledge Augmentation for Language Models KV Caching LLM Fine-Tuning Retrieval-Augmented ICL

Sep 15, 2026cs.LG

TAME: Token Attribution and Masking for Emergent misalignment

Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignment (EM). Prior work has localized EM in model weights, activations, and training documents, but it remains unclear which training tokens carry the relevant fine-tuning signal. We introduce TAME (Token Attribution and Masking for Emergent Misalignment), a three-stage framework: token attribution scores how strongly the fine-tuning update raises each response token's likelihood, using forward passes through a released LoRA adapter; signal characterization finds patterns among high-attribution tokens; and causal validation tests them by attribution-guided loss masking. On released EM organisms and a 6,849-example medical-advice split, attribution is concentrated (the top 5% of tokens hold 32% of the mass) and, in Llama, depleted for medical vocabulary but enriched for a register of unwarranted certainty, even after controlling for token rarity. Masking high-attribution tokens during fresh fine-tuning cuts EM by 23x in Llama and 36x in Qwen, with the perplexity cost concentrated on the targeted register rather than on medical content; an equal random mask leaves EM unchanged. In Llama, the attribution pattern suggests that EM-relevant signal lies more in how confidently flawed content is expressed than in its domain vocabulary; the causal masking effect itself holds across both model families.

Md Rayhanul Masud, Md Rizwan Parvez

University of California, Riverside · 2Qatar Computing Research Institute (QCRI)

LLM Interpretability LLM Fine-Tuning Emergent Misalignment in Language Models Causal Interventions in Language Models

Sep 14, 2026cs.CL

ReMova: Fine-tuning LLMs for English to Belarusian translation

This paper presents a Belarusian-specific data-cleaning pipeline and fine-tuning for English-Belarusian machine translation. Our cleaning pipeline distinguishes itself from others by employing a correction tool that addresses the issue of the two orthographies of the Belarusian language, noise in the training data, interference from other languages and other misspelling issues common in Belarusian on the internet. A matched ablation on unfiltered training data shows substantial benefits from filtering for all fine-tuned models, with the LLM-based models gaining roughly twice as much from filtering as the dedicated encoder-decoder MT system, supporting the view that for Belarusian MT one of the primary bottlenecks is data quality.

Mikita Pilinka, Aliaksandr Kliujeŭ, David Samuel +1

University of Oslo Department of Informatics · Independent Researcher

LLM Fine-Tuning Low-Resource MT Low-Resource Language Processing Machine Translation

Sep 14, 2026cs.LG

Clustering-Based Balanced Sampling and Allocation with Data Parallelism for High-Performance Fine-Tuning

Instruction-tuning datasets for large language models (LLMs) are often large, redundant, and imbalanced, limiting efficient adaptation. Naive large-batch fine-tuning repeatedly includes overrepresented sample groups while weakly covering underrepresented but informative ones, especially under data parallelism (DP) across multiple GPUs. We propose CluSTER, a Cluster-aware balanced Sampling framework for Training Efficient data Reduction in DP instruction tuning. CluSTER curates a representative reduced dataset through gradient-space clustering and DP-aware balanced allocation, ensuring dual-level coverage across clusters and workers, while preserving the original data distribution by weighted update. As a result, CluSTER reduces redundant computation and improves training stability without compromising model quality. Across multiple instruction-tuning datasets, CluSTER reduces training time by up to 69.6% with almost no accuracy loss compared to prior sampling and data reduction methods. Code is available at https://github.com/kaist-dmlab/CluSTER.

Hyunjin Kim, Youngeun Nam, Jaemin Han +2

KAIST

LLM Fine-Tuning Instruction-Tuning Data Selection Distributed Training Instruction Tuning

Sep 14, 2026cs.CL

Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking

Advanced large language models (LLMs) with long context windows can substantially reduce input truncation in document-level machine translation (DocMT). However, direct Doc2Doc translation remains prone to n-gram repetition and progressive quality degradation. A common remedy is to segment the document into finer-grained chunks. Nonetheless, conventional rule-based chunking approaches fail to handle the length distribution mismatch between training and inference. To address this, we introduce Fixed-Range Chunking (FRC), utilizing dynamic programming to partition documents into chunks within a predefined length interval. By consistently applying FRC during training and inference, the input documents of any length are mapped to the same length distribution, substantially reducing train-test length mismatch. Centered on FRC, we propose a lightweight dual-boundary matching algorithm for chunk alignment, alongside four distinct training strategies. Experimental results show that FRC-based fine-tuning substantially improves 7B LLMs over direct Doc2Doc fine-tuning and outperforms existing DocMT methods on IWSLT2017. We further construct GlobVDoc, a 10-language test set independent of mainstream DocMT training sources, and show that FRC improves out-of-distribution document translation.

Xiaotian Wang, Youyuan Lin, Zhan Shen +1

The University of Tokyo · Riken · Kyoto University +1

Document Chunking LLM Fine-Tuning Document-Level MT Machine Translation

Sep 11, 2026cs.AI

Scaling Clinical Judgment to Evaluate Medical AI

Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs). This is difficult to scale; thus, prior studies typically rely on small physician panels, often from a single institution or specialty, which both limits the scientific questions investigated and makes it unclear whether findings would be reproduced with a different set of evaluators. To more rigorously and scalably study clinical reasoning in AI models, here we introduce PrecepTron, an LLM fine-tuned for physician-level evaluation of open-ended responses. PrecepTron was trained using low-rank adaptation (LoRA) of a 32-billion-parameter model on a small number of physician examples. We also release GRAND-ROUNDS, a new large-scale physician-annotated benchmark of 9,217 scored responses from 160 clinicians across seven studies. We show that frontier LLMs in typical "LLM-as-a-judge" approaches often disagree with physicians and with each other, but fine-tuning PrecepTron on a small number of cases enables physician-level consistent scoring across tasks. We use PrecepTron to reproduce headline findings from five influential studies assessing LLMs for clinical care in JAMA, Science, and Nature Medicine without new human grading. Using PrecepTron, we then pose new questions about how LLMs reason in medicine that would have been infeasible with human grading alone, including measuring the diagnostic accuracy of frontier LLMs when clinical cases are provided piecemeal, even token by token. Together, PrecepTron and GRAND-ROUNDS provide a foundation for reproducible, large-scale study of how LLMs reason in medicine. All code, data, and labels are made freely available for researchers.

Thomas A. Buckley, Zahir Kanjee, Peter G. Brodeur +15

Department of Biomedical Informatics, Harvard Medical School, Boston, MA · Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA · Stanford Division of Hospital Medicine, Stanford University, Stanford, CA +11

LLM-as-a-Judge LLM Fine-Tuning Clinical Reasoning Clinical Language Model Evaluation Medical LLMs

Sep 10, 2026cs.CL

Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss

Large language models are typically trained under uniform token weighting, which allows frequent and low-information tokens to dominate learning and can increase the tendency to memorize surface-level text spans. To address this, we present an information-weighted cross-entropy loss that rescales token-level contributions using TF-IDF statistics, emphasizing semantically informative tokens while down-weighting ubiquitous ones. Experiments on five decoder-only LLMs ranging from 1.1B to 13B parameters show consistent reductions in memorized substring length while preserving perplexity and downstream task performance. Under LoRA fine-tuning, TF-IDF reduces average substring memorization length by 14% across all five models. Under full-weight fine-tuning on TinyLLaMA 1.1B, the reduction reaches 58%. Our approach is architecture-agnostic and can be incorporated into existing training pipelines with less than 3% computational overhead, offering a lightweight and principled way to mitigate memorization without disrupting standard training dynamics.

Zhijian Li, Stefan Larson, Kevin Leach

University of Southern California, Los Angeles · Vanderbilt University, Nashville

Memorization in Language Models LLM Fine-Tuning LLM Training

Sep 9, 2026cs.CL

Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors during fine-tuning and removes them at evaluation time, yet the mechanism behind its lasting protection remains unclear. Analyzing its temporal optimization dynamics, we find that the defense emerges from an early compensatory adaptation phase followed by a steady-state phase where the corrective signal decays; in parameter space, attention output projections emerge as the dominant residual-write route for defensive updates. Through Intervention Delta Preservation (IDP) and IDP Continuation experiments, we further show that preserving or reinjecting the weight offset fails to maintain protection, indicating that preventative steering relies on active adaptation rather than a static defense. Motivated by this finding, we propose Progressive Intensity Scheduling (PIS), which starts with a moderate injection strength and increases it after static-strength alignment begins to decay. Across the evaluated Qwen2.5 and Gemma-3 models, PIS improves safety robustness over static-strength steering while reducing harmful trait expression.

Jing Guan, Yachao Yang, Zhaoliang Liu +3

JIUTIAN Research, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China

LLM Fine-Tuning Adversarial Attacks on LLMs Adversarial Robustness of Language Models

Sep 7, 2026cs.LG

MpSub: A Momentum $p$ -Dimensional Subspace Trust-Region Method for Derivative-Free Fine-Tuning of Large Language Models

Full-parameter fine-tuning of large language models has substantial memory costs because backpropagation stores activations and gradients. Zeroth-order optimization avoids this by estimating update directions from loss evaluations, but existing methods require tuning a sensitive learning rate for each model and task. We propose the momentum

p

-dimensional subspace trust-region method (MpSub). At each iteration, MpSub searches within a

p

-dimensional subspace: one direction preserves historical momentum from the most recent accepted step, while the remaining directions explore via fresh random sampling. The subspace gradient is estimated by central differences, a trial step is computed from a linear trust-region model, and the trust-region radius adapts according to the agreement between predicted and observed loss reduction, eliminating the learning rate. For LLM fine-tuning, evaluations within an iteration share a minibatch, and directions are regenerated in place from seeds, using forward passes alone. For smooth deterministic objectives under unorthogonalized Gaussian directions, we bound the finite-difference error, quantify gradient energy captured by the subspace, and prove that

\lim_{k\to\infty} \|\nabla f(x_k)\|_2 = 0

almost surely under a safeguarded radius update. Under a matched budget of 8,400 training-objective forward passes, we fine-tune OPT-125M and OPT-350M on CommitmentBank. With the same preset parameters at both model sizes, MpSub attains mean test accuracies of 0.673 and 0.690 over three seeds, matching tuned MeZO (0.685) without any learning-rate search.

Yuyang Wang, Haoyu Yao, Pengcheng Xie

Xi’an Jiaotong University, Xi’an, China · Lawrence Berkeley National Laboratory, Berkeley, CA, USA

Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning Trust-Region Optimization

Sep 2, 2026cs.AI

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training

Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomplete. Task-level natural-language priors can provide useful guidance in such settings, but existing approaches usually treat these priors as input context rather than as learning signals during training. We propose Prior-Guided Tuning (PGT), a training perspective that incorporates natural-language priors as auxiliary learning signals for low-resource LLM training. Under this perspective, we introduce Contrastive Prior Steering (CPS), which keeps the original supervised objective intact while adding positive and negative prior-conditioned auxiliary losses to encourage task-consistent learning and discourage plausible but misleading alternatives. Experiments on AmbiMath, Jigsaw, and MNLI/HANS show that CPS consistently improves over plain and prompt fine-tuning. On AmbiMath, CPS achieves 97.6% average exact-match accuracy. On Jigsaw, CPS improves average Macro F1 by 9.5 percentage points over standard fine-tuning, and with 1/10 of the experimental training data slightly exceeds full-data plain fine-tuning. On HANS, CPS improves non-entailment accuracy by 8.3 and 5.2 percentage points for LLaMA 3.1 8B and Qwen 2.5 7B, respectively, while maintaining comparable in-domain MNLI accuracy. These results support our central claim: task-level natural-language priors can provide useful guidance as auxiliary learning signals for low-resource LLM training. Our code and data will be publicly available.

Jian Gao, Xiao Zhang, Xun Zhu +2

College of AI, Tsinghua University · Department of Electronic Engineering, Tsinghua University

LLM Fine-Tuning Data-Efficient Learning

Sep 1, 2026cs.CR

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior work often attributes this failure to gradient conflict, we propose a fundamentally different Fisher-geometric explanation: safety Fisher is low-rank, and alignment makes the safety geometry flatter while preserving an output-routing pathway. After 100 benign fine-tuning examples, this pathway is selectively re-sharpened in output-side MLP modules, explaining the asymmetric fragility: safety can collapse to high attack success rates, while general utility degrades mildly. The routing view also explains why few safety examples can restore refusal behavior, indicating that internal safety-relevant representations are preserved. Finally, we show that LoRA and ASAM mitigate early collapse by suppressing output-side sharpness, but their protection weakens at larger fine-tuning scales. Overall, safety failure is best understood as a disruption of a low-rank output-routing mechanism

Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2

Indiana University Bloomington · Tsinghua University · Nanyang Technological University

LLM Fine-Tuning LLM Safety Alignment

Sep 1, 2026cs.AI

Automated Event Log Generation from Unstructured Text Using Finetuned LLMs

Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM techniques is strictly predicated on the availability of structured event logs. Thus far, event logs have often been laboriously created by domain and process mining experts. This costly effort causes large portions of organizational knowledge, including incident tickets, manuals, and textual reports, to remain underutilized. We address this bottleneck by investigating the efficacy of Large Language Models (LLMs) as automated data translators. We propose a scalable framework that leverages LLMs as data translators to bridge the gap between unstructured textual resources and structured event data. We finetune LLMs on a newly created text-to-log dataset, demonstrating that the resulting models can extract high-fidelity event logs from unstructured resources. Our results show that this finetuning approach outperforms few-shot or zero-shot prompting by a large amount, highlighting finetuning as a necessary pre-condition for generating reliable event data. We conclude that our method provides a promising pipeline for making previously unused data available to process mining ecosystems, effectively expanding the possibilities of using PM to further investigate organizational workflows.

Maximilian Seeth, Gabriel Marques Tavares, Daniel Schuster

LMU Munich, Germany · University of Mannheim, Germany

Process Mining LLM Fine-Tuning LLM Information Extraction

Sep 1, 2026cs.AI

Prompt-Robust Language Models: Which Training Strategies Work?

Despite their strong performance, large language models remain highly sensitive to prompt formulation. Prior work addresses this through refined data construction or through dedicated robustness objectives. We reproduce and compare these strategies under controlled conditions, and measure how effective they are in addressing models' prompt sensitivity. We find the current robustness fine-tuning methods improve over standard fine-tuning and in-context learning, but the best-to-worst prompt gap remains as high as 40-57% of performance. Moreover, the recent robustness-enhancing methods we test - CoIN for contrastive alignment and PPCL for consistency regularization - often fail to outperform the simplest data construction strategy: training on one template per batch. Our diagnostics explain these results. The auxiliary objectives move the quantity they penalize, but do not generalize beyond it. Additionally, data construction strategies differ due to the conflicting signs of per-template gradients on 57-64% of parameters. Thus, batches that mix formulations force the optimizer to reconcile competing updates instead of finding a shared, prompt-agnostic one.

Frederic Sadrieh, Michal Štefánik

Center for Information and Language Processing, LMU Munich · R&D Centre for Large Language Models, National Institute of Informatics, Japan

Prompt Sensitivity LLM Fine-Tuning Language Model Robustness Prompt Robustness