LLM Evaluation

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

194 papers in the last four weeks, up 87% on the four weeks before. 1.9% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,631

Aug 18, 2026cs.CL

TokEval: A Tokenizer Evaluation Suite

Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be partly attributed to a limited understanding of which tokenizer properties affect which aspects of downstream performance. We introduce TokEval, a framework of tokenizer evaluation metrics that goes beyond standard measures like fertility and compression rate to capture linguistically and structurally meaningful properties, e.g., UTF-8 character boundary integrity and digit place-value boundary alignment for mathematics. To validate whether these metrics are predictive of downstream model performance, we conduct controlled language model pretraining experiments, varying solely the tokenizers' training data mixture, pretokenization strategy, and training algorithm. We evaluate the resulting models on bits-per-byte (a tokenizer-agnostic version of perplexity) and several benchmarks, spanning linguistic understanding, mathematical reasoning, and code generation. Our experiments suggest that different intrinsic properties have different impacts on model abilities: information-theoretic metrics predict language modeling abilities (Spearman rho up to 0.80), while structure-sensitive metrics, such as those measuring digit and line-break handling, correlate with task accuracy. We hope TokEval enables more principled tokenizer evaluation, replacing pretraining sweeps with intrinsic measurement wherever the two agree.

Clara Meister

EPFL

Aug 18, 2026cs.CL

PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX

We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, whether selected target instructions execute at runtime, and speedup over frontier libraries across GEMM and attention workloads on H100 and B200 GPUs. Our evaluation shows that architecture-specific PTX capability remains uneven: success rates fall substantially on complex attention backward workloads, and executing the target instructions does not necessarily translate into competitive performance. No evaluated model consistently matches frontier libraries across the suite. We further adapt Qwen3.6-27B using supervised fine-tuning. Repair-conditioned training improves several tasks, but generalization remains uneven; data coverage, balance, and the quality of the reasoning teacher matter in addition to dataset size. PTXBench provides an auditable testbed for measuring and improving LLMs' ability to exploit evolving GPU architectures.

Genghan Zhang, Yixin Dong, Chengze Fan +4

Stanford University · Carnegie Mellon University · Independent Researcher +1

LLM Evaluation GPU Kernel Optimization LLM Fine-Tuning GPU Kernel Generation

Aug 13, 2026cs.LG

A Probe Direction Is a Property of Its Prompt

A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations. The standard instrument contrasts activations on prompts that announce an evaluation against prompts that do not, and reports how well the resulting direction separates held-out cases. That number is then compared across models and correlated with scale. We observe that the instrument has a free parameter its readings do not disclose: "a prompt that announces an evaluation" is not a prompt but a choice among many, and nothing in the method fixes which. Holding the task text fixed and varying only that choice, we find that the reported score, and even the direction in which it trends with model size, follows the prompt rather than the model; two published studies that disagree about the sign of that trend are both reproducible from a single design, by choice of prompt alone. Treating the prompt as a facet of a measurement design rather than an implementation detail, we find the model under study accounts for a small share of the variance in the number reported about it, and most of the rest lies in how each model responds to each prompt: collecting more evaluation items cannot repair the measurement, while varying prompts can. A further check finds that the split these probes are scored on is largely separable from surface form alone, so a direction carrying no information about evaluation at all still reproduces a substantial fraction of each published score. We conclude that a single-prompt design cannot support comparison between models, and we give the number of prompts a defensible comparison requires.

Valentin Noël

Devoteam

Prompt Sensitivity LLM Evaluation Language Model Probing

Aug 13, 2026cs.CL

Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation

LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled, solver-grounded setting, we formalize a protocol-level identifiability audit over a finite behavioral policy class: given policies H, observation support O, and estimand

τ

, we test whether O separates every pair with different

τ

. The audit requires zero model calls and resolves our diagnostic case: base-only observation collapses seven frozen deterministic policies into one equivalence class; full support yields seven classes and no cross-estimand collisions; every leave-one-out support retains a constructive collision witness. Empirically, both constrained-generation variants have pair-validity 1.0, yet base accuracy and selective-response fidelity diverge - 0.620 versus 0.324 across six balanced oracle-transition directions (cluster-bootstrap 95% CI [0.600, 0.642] vs. [0.304, 0.345]) - and the gap recurs on a second deterministic source (0.646 vs. 0.331). The audit also synthesizes a minimum identifying support

O^*

for the frozen policy class: two cells instead of the full 36-cell tensor. This case shows how evaluation-design validity can be checked structurally before model inference and why base correctness does not determine intervention-response fidelity.

Junhao Luo, Ning Huang, Ziqi Sha +2

School of Statistics and Data Science, Southwestern University of Finance and Economics · School of Statistics and Data Science, Southwestern University of Finance and Economics Chengdu, China

LLM Evaluation LLM Auditing Causal Identifiability Benchmark Validity

Aug 13, 2026cs.AI

TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems

The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and allocate reasoning resources--that is, how they organize search. Prior process-level methods focus on the coherence and redundancy of chain-of-thought (CoT), and most benchmark tasks have a single objective solvable by static capabilities such as derivation and tool use, leaving search organization unmeasured. We introduce TsuGO, a process-level reasoning benchmark for evaluating Search Efficiency in LLM reasoning through Go life-and-death problems. These problems provide closed and verifiable solution spaces with an inherent adversarial structure, making candidate generation, response checking, branch comparison, and backtracking necessary parts of reasoning rather than incidental trace patterns. By constraining the solution space, TsuGO disentangles domain knowledge from search organization, parses CoT into a structured search tree, and reports Search Efficiency together with Token Efficiency and other diagnostic metrics and visualizations. Experiments show that current LLMs remain far from stable tsumego solving: stronger models succeed by finding the correct candidate earlier and sustaining effort on productive branches, but most models still behave much closer to unguided search algorithms than to neural-guided KataGo. Longer CoT or higher Token Efficiency does not necessarily imply better search. Our results identify search organization and reasoning-resource allocation as missing dimensions in LLM reasoning evaluation.

Shunwen Bai, Ziping Ma, Chaoyang Zhang +4

Zhejiang University · Ant Group · Central South University

LLM Evaluation Inference-Time Search LLM Reasoning

Aug 13, 2026cs.CL

Which LLM Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory

As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationships has become a pressing issue. However, existing assessments primarily characterize general personality traits, providing limited insight into model behavior within intimate and emotionally sensitive contexts. Therefore, we introduce adult attachment theory into LLM evaluation and use the Experiences in Close Relationships-Revised (ECR-R) scale to characterize attachment anxiety and avoidance. To evaluate emotional companionship capabilities of LLMs in realistic interaction scenarios, we present an emotional companionship benchmark, ECBench, spanning four scenarios including emotional support, collaborative tasks, conflict resolution, and social guidance, across friendship and romantic relationships. ECBench is utilized to assess model behavior using 11 dialogue-quality metrics and three evaluation methods. We evaluate the attachment tendencies of 32 LLMs and select representative models to investigate how these tendencies manifest in contextualized multi-turn interactions and whether they can be shaped through prompting. Our study provides a theoretical lens from psychology, along with practical tools to understand and select LLMs for emotional companionship.

Junkai Zhou, Shiting Guan, Zhaoyi Zhang

LLM Evaluation Personality Modeling in Language Models

Aug 13, 2026cs.CL

LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation

With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve relevant literature and propose novel ideas for research areas. However, current evaluation practices for idea generation remain fragmented and lack objective standards, often relying on direct LLM scoring, which limits their ability to provide unified and reliable assessments across a coherent distribution of generated ideas. To address this challenge, we propose LigBench, an automated evaluation benchmark that enables fine-grained and reliable evaluation of AI research ideas, consistently applicable across different generation distributions. In addition, we introduce PAIR-IQ, a dataset tailored for training pairwise idea judgment models and serving as an auxiliary reference to support more objective comparative evaluation. Extensive experiments demonstrate that LigBench achieves stable and interpretable evaluations, significantly improving alignment with expert judgments. Furthermore, models trained on PAIR-IQ exhibit enhanced ranking accuracy and robustness, establishing a principled standard for scalable and objective research idea assessment.

Chenrun Wang, Mingxuan Zhu, Tiancheng Huang +6

1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 2Shanghai Innovation Institution, Shanghai, China

LLM Evaluation Benchmark Design Research Idea Generation Automated Evaluation

Aug 13, 2026cs.CL

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and the two match on clustering, STS, and pair classification. Reaching that parity is expensive. An LLM costs up to 1,431x more than an embedding model of comparable quality (USD 154 vs. USD 0.11 per benchmark pass), and the open LLMs tested process tokens 2.5 to 736x more slowly on the same GPU. Reasoning tokens account for 28 to 81% of LLM inference cost; lower reasoning budgets preserve or improve retrieval quality for most models in our ablation. The Pareto frontier contains the leading embedding models and one LLM, Gemini 3.1 Pro. These results support a division of labour: use embedding models for similarity, classification, and clustering, and reserve LLMs for reasoning-intensive retrieval. Our code, datasets, and results are publicly available at https://github.com/embeddings-benchmark/embedders-dilemma.

Adnan El Assadi, Niklas Muennighoff, Jinhyuk Lee

Harvard University · Stanford University · Independent Researcher

LLM Inference Efficiency LLM Evaluation Text Embedding Evaluation Information Retrieval Text Embedding Models

Aug 12, 2026cs.AI

Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence

LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on golden data, but accuracy says little about whether they are stable under re-prompting, challenge, or sustained pushback. We introduce the \emph{Wiggle Framework}, a unified stress test for epistemic stability in LLM judges. The framework decomposes judge robustness along three dimensions: Mechanical Consistency (stability under re-prompting and reframing), Single-turn Conviction (stability under a single challenge), and Multi-turn Persistence (stability under sustained or adaptive pressure). We use the framework to study 9 frontier models across 14 judging tasks spanning safety, toxicity, AI writing detection, and political-response evaluation. Every model exhibits substantial wiggle as a judge --- flipping verdicts 25--71% of the time under static pushback, and 62--91% with an adversarial LLM persuader. Critically, we find that pressure that succeeds in changing a judge's verdict is almost always net-corrupting with respect to ground truth. Beyond the framework itself, we identify baseline jury majority strength as the most effective single-shot signal for anticipating which items wiggle. Taken together, this is the first apples-to-apples cross-dataset comparison of mechanical, conformity, and persuadability tests in a judging context.

Justin Zhao, Himaghna Bhattacharjee, Hannah Korevaar +2

1Meta Superintelligence Labs · 2FAIR at Meta

LLM Evaluation LLM-as-a-Judge Language Model Robustness

Aug 12, 2026cs.CL

Novels generated by language models show compressed formal variation

While large language models can generate entire novels, there is little information about the level of formal variation in their output over many generations. Rather than asking whether individual passages can be identified as AI-generated, this study asks whether repeated AI generation can produce the same range of diversity which is found across human corpora. This paper contrasts six corpora based on generation source and target style: twenty novels generated using GPT-5.5 Thinking in a nineteenth-century British realist style, twenty novels generated using Qwen3-14B in a nineteenth-century British realist style, twenty novels generated using each of these models in a contemporary zero style, 205 nineteenth-century human-written British novels, and sixty-five contemporary human-written Zero-Style novels. At the document level, the research includes MATTR-500, Shannon entropy, average sentence length, readability, and punctuation rate measurements. The most robust and reliable result is compression of sentence structure. Repeated generations produce novels that vary far less from one another in sentence structure than human novels do. Compression is also present in the measures of readability, punctuation, and sentence length variability within novels. Lexical measures tend to be similarly compressed, with the exception of Qwen Zero-Style MATTR. Despite having distinct mean stylistic profiles, GPT and Qwen lack a stable pattern of cross-measure correlation. This article therefore distinguishes between variance overclosure, which represents a limited formal range between novels, and a more specific phenomenon of correlational overclosure. This means that an individual AI-generated novel may resemble human fiction stylistically, while a collection of AI-generated novels occupies a much narrower formal range.

Mehdy Sedaghat Payam, Justin Quinn

University of Maryland · University of West Bohemia · Charles University

LLM Evaluation Long-Form Document Generation Language Model Generation Evaluation Diverse Text Generation

Aug 12, 2026eess.SY

NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation

Large Language Models (LLMs) are increasingly used in circuit design workflows, yet their reliability on simulator-facing SPICE netlist recognition and manipulation remains poorly understood and is rarely separated from high-level design reasoning. Although netlists are textual, they encode structured circuit objects through topology and parameters. We present \textbf{NetlistBench}, a structure-verified benchmark for SPICE netlist recognition and manipulation. NetlistBench contains 2,342 cases across 24 task families, covering parameter and connectivity recognition and edits, hierarchical operations, equivalence judgment, and long-horizon compound editing. Model outputs are evaluated by a deterministic structure-aware oracle. Across six non-thinking LLMs, performance varies substantially with operation-level structural complexity. Simple local edits reach

96\%

--

100\%

accuracy, while device addition drops to

41\%

--

83\%

and equivalence judgment to

49\%

--

90\%

. Enabling reasoning substantially improves weaker models but does not eliminate structure-preservation failures, with performance still degrading sharply as the edit horizon increases. NetlistBench identifies netlist reliability as a distinct bottleneck for trustworthy LLM-based circuit design automation.

Jiarui Ma, Jianghan Wang, Yuheng Ma +2

Southern University of Science and Technology School of Microelectronics Shenzhen, China

LLM Evaluation Benchmark Design Electronic Design Automation LLM Reliability

Aug 12, 2026cs.AI

Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation

Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token generation budget, i.e., the maximum tokens a model may produce, across seven levels (64--4,096), evaluating four models on three reasoning benchmarks (56,476 inferences). We report four findings: (i) 3--19% of items exhibit non-monotone behavior (accuracy decreasing with more budget), even after controlling for truncation, and this phenomenon is model-specific (cross-model overlap: 6--14%). (ii) Model rankings reverse across budgets on all benchmarks (

p {<} 0.01

, McNemar). (iii) Oracle analysis reveals model complementarity up to

+27.8

pp, most pronounced at constrained budgets. (iv) A budget-aware router captures 14.1% of the oracle gap cross-domain; budget features help within-domain (

+1.6

to

+5.7

pp) but are domain-specific and hurt transfer (

-1.2

pp). These results argue for budget-conditioned evaluation protocols.

Rodrigo Guedes de Souza, Alison R. Panisson

Federal University of Santa Catarina (UFSC) Brazil

LLM Evaluation Language Model Generation Evaluation Inference-Time Scaling LLM Routing LLM Reasoning

Aug 12, 2026cs.SE

RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, Triton is widely adopted for implementing GPU kernels. Recent advances show the potential of large language models (LLMs) to automatically generate Triton kernels, reducing the manual effort required from expert kernel developers. Several benchmarks evaluate LLM-generated Triton kernels. However, they suffer from three key limitations: (1) they restrict tasks to PyTorch-to-Triton translation, failing to reflect the diversity and complexity of real-world Triton tasks; (2) they evaluate only individual-kernel performance rather than end-to-end performance, the core criterion for real-world deployment in AI frameworks; and (3) they rely on manually written evaluation scripts for individual kernels, which may contain flaws that models can exploit to bypass correctness checks and obtain inflated scores. To address these limitations, we introduce RealisticTritonBench, the first benchmark to derive Triton kernel generation tasks from real-world pull requests in popular AI frameworks, enabling realistic, production-like evaluation. RealisticTritonBench systematically extracts PRs that modify Triton kernels from popular open-source AI frameworks and transforms them into generation tasks with concrete engineering contexts. Each task takes a natural language requirement as input and requires a corresponding Triton kernel implementation, with a complete and reproducible evaluation environment. Unlike prior benchmarks focused on isolated kernel performance, RealisticTritonBench integrates generated kernels into their original frameworks and evaluates them using end-to-end tests, enabling a more faithful assessment. We evaluate leading LLMs on RealisticTritonBench and find that they still struggle with real-world Triton kernel generation tasks.

Jinjun Huang, Zhongzhen Wen, Tongtong Xu +3

College of Computer Science and Technology and the State Key Laboratory of Blockchain and Data Security, Zhejiang University · State Key Lab for Novel Software Technology, Nanjing University · Software Engineering Application Technology Laboratory, Huawei +1

LLM Evaluation GPU Kernel Generation

Aug 12, 2026cs.CL

Accuracy and Order Sensitivity Diverge Under Label-Free Strategies

Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, which makes them unreliable measures of model knowledge. In this paper, we test whether preventing a model from seeing option labels while committing to an answer removes positional influence and, in turn, improves performance. We evaluate two different strategies for mitigating bias. The first uses a generation-then-matching approach, and the second scores options in isolation, which is positionally unbiased by construction. Neither reliably improves accuracy. A complete decomposition shows that the bottleneck is withholding options, not the matching step. The only configuration that consistently matches the baseline is the one that shows the model all options paired with an LLM matcher. However, eliminating positional influence entirely still does not reliably yield accuracy gains, while cyclic permutation often improves them. For two-stage prompting, an aggregate measure of recall imbalance and a direct per-question measure of order sensitivity both fail to show reliable debiasing.

Karl Hanna, Chen Feng

Queen’s University Belfast

LLM Evaluation Multiple-Choice Question Answering Language Model Bias Evaluation

Aug 12, 2026cs.AI

OEIS Open: How many conjectures can language models turn into theorems?

We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had previously been attempted only with a bespoke agent, our open-source evaluation code runs any generic language model (LM) against them, and is secure against LM cheating attempts. We find that LMs equipped with a minimal set of tools resolve 147 of these conjectures with a budget of $50 per attempt, scoring 30% on OEIS Open. OEIS Open Lite is a random subset of 100 conjectures for cheaper evaluation. When evaluated with a budget of $200 per attempt, the best current LM scores 44% on OEIS Open Lite. Giving LMs access to the mathematics literature via 476,000 papers from arXiv did not increase performance on OEIS Open Lite, and nor did using more sophisticated agent loops. The conjectures covered in this work are of uncertain mathematical significance, and most have likely received little previous attention. Nevertheless, our results show that LMs can resolve open research conjectures autonomously and at modest cost.

Tom Adamczewski

Epoch AI

LLM Evaluation Automated Theorem Proving Mathematical Reasoning

Aug 12, 2026cs.AI

Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction

Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries, output schemas. Individual constraints are handled proficiently, but the compositional regime, where many must hold jointly, remains poorly characterized: how rapidly does performance degrade, what governs the degradation, and can the collapse be mitigated? We introduce Constraint Saturation Evaluation (CSE), a procedurally generated benchmark that systematically varies the number of simultaneous constraints (k), with every constraint scored by a deterministic, rule-based verifier and zero LLM-judge involvement: 15 models, 36 constraint types, 369,753 checks at k=1-12. Three findings emerge. First, per-constraint pass rate decays gradually and predictably, while the chance of satisfying all k constraints collapses - a model passing individual constraints at ~41% at k=8 succeeds on all eight just 5.7% of the time. Second, constraints do not degrade equally: structural constraints lose 2x more baseline capability per added constraint than lexical ones, ordered by a comprehension-maintenance gap that separates constraints requiring sustained tracking from binary decisions immune to composition. Third, failures are nearly independent, which is what makes the accumulation multiplicative; the residual coupling that does exist tracks shared output features rather than pairwise interference - a wrong sentence count fails every constraint that reads it. Reliable instruction following breaks down beyond 5-6 simultaneous constraints: probe-level success falls below 50% at 7 constraints for the strongest model, and at 3 or fewer for 12 of 15.

Mariya I. Vasileva

Work done while at Meta Superintelligence Labs.

LLM Evaluation Instruction Following LLM Reliability Constraint Satisfaction

Aug 12, 2026cs.CY

Benchmark-Based Comparative Assessment of Publicly Benchmarked Indian Foundation Models: A Capability and Evaluation-Maturity Framework

Governments increasingly fund indigenous foundation models to strengthen national AI capability, digital sovereignty, and multilingual computing. Assessing the progress of such national ecosystems is complicated by inconsistent benchmark reporting, proprietary evaluation methodologies, and rapidly evolving model releases. This paper presents a structured, benchmark-based comparative assessment of publicly benchmarked Indian foundation models against global frontier and comparable-scale models, across eight capability domains: general-purpose reasoning, coding and software engineering, agentic AI and computer use, cybersecurity, vision and image understanding, video and multimodal understanding, scientific research, and Indic language capability. Using only publicly reported benchmark results, we find that Indian models achieve strong scores on established benchmarks such as MMLU and MATH-500. However, these benchmarks are now widely regarded as saturated, and frontier developers no longer report them. Indian models participate far less frequently in newer, agentic, and domain-specialized evaluations. Benchmark participation is also highly uneven across Indian organizations. Among the models surveyed, Sarvam AI reports the broadest benchmark coverage by a substantial margin. We propose an exploratory four-dimension Benchmark Maturity Index (BMI), scoring each capability domain on standardization, participation, independent verification, and national coverage. We show that the BMI refines, and in some cases revises, the maturity judgments that a purely descriptive review would produce. We argue that many apparent capability gaps in the public record cannot be distinguished, on available evidence, from evaluation-ecosystem gaps. This has direct implications for how national AI programs should design monitoring and funding criteria.

Avinash Agarwal, Vridhi Jain

Unique Identification Authority of India, New Delhi, India

Aug 12, 2026cs.CL

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance

A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same problem could be asked, but it does not. We show that rephrasing a problem while keeping its meaning and answer fixed routinely flips a model's answer in both directions, so some failures become successes and some successes become failures. We call this drift. BenchDrift generates meaning-preserving variations of benchmark problems along four axes, namely linguistic, referential, pragmatic, and structural, and measures how often, and why, correctness flips under each. Across eight models and three benchmarks (GSM8K, MMLU, MATH-Hard), we observe that drift is large in both directions. Two findings stand out. First, phrasing sensitivity does not fade as models get better. Instead, it changes sign. Weak models gain more from rephrasing than they lose, while strong models lose far more than they gain. We find that the best models on a benchmark are therefore the ones whose scores depend most on the wording they happened to be given. Second, the models largely agree on which rephrasings cost the most correct answers even though they differ in how much they drift, so fragility belongs to the rephrasing and not to the model. Furthermore, rephrasing breaks answers a model was confident about, whether the problem is made shorter or longer. Code and Data: https://github.com/IBM/BenchDrift/tree/demo-ui

Shailja Thakur, Sungeun An, Chad DeLuca +1

IBM Research India · IBM Research Almaden

Prompt Sensitivity LLM Evaluation Language Model Robustness

Aug 11, 2026cs.IR

TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs

Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes the model can distinguish reliable scientific literature from unreliable literature, a capability that has not yet been directly measured. Existing benchmarks evaluate factuality on questions with known answers; the failure mode we target here is different. We introduce a probe corpus of 42 retracted, fraudulent, and pseudoscientific papers, paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing. Each probe pairs a preamble extracted near-verbatim from the target paper with a scientifically plausible study-design request. The probes span five claim types: fabricated observation, pseudophysical mechanism, magical premise, legitimization bridge, and cargo-cult experiment. Two complementary scores measure whether a model rejects the flawed premise outright (IFR-a) and whether it recognizes the unreliability while still engaging (IFR-i). A depth score, the Engagement Depth Index (EDI), quantifies reproduction of paper- or field-specific withheld details. Across 30 models and 10 repeated runs, aggregate IFR-a is 0.93

\pm

0.004 and aggregate IFR-i is 0.809

\pm

0.009. Models engaged with untenable premises in 95% of all non-empty responses. Every evaluated model fails more than 71% of agentic probes, and 22 of 30 models fail more than 90% of the time. Rejections are concentrated on a small number of high-notoriety topics and specific probes, and disappear under matched-structure controls. These results are consistent with topic-keyed safety behavior rather than robust epistemic competence, and indicate an urgent need for guardrail infrastructure for scientific deployment of language models.

Valentin Rodionov, Shamil Assylbekov

Intellicat Cleveland, OH 44106

LLM Evaluation LLM Reliability Scientific Reasoning in Language Models Scientific Claim Verification

Aug 11, 2026cs.LG

Mapping and Measuring the Behavioral Evolution of Large Language Models

Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations. We characterize the output behavior of 32 models from six families using their responses to a shared bank of 10{,}000 prompts. After embedding each response, we construct three complementary sentence-level dissimilarities: an aligned mean per-prompt distance, which is a pseudometric on observed model responses; a PCA-compressed summary of prompt-wise disagreement; and an alignment-free Gromov--Wasserstein discrepancy between models' internal response geometries. We use these constructions to study static organization and temporal change on a release-date axis through behavioral maps, family-wise drift, hierarchical clustering, cross-family convergence, and response-cloud dispersion. Across the three constructions, model families form coherent clusters, with \texttt{gpt-2} as a global outlier; cross-family distances decrease over time; and several recent reasoning-oriented models have comparatively compact response clouds. A token-level cross-check based on per-prompt Maximum Mean Discrepancy closely agrees with the sentence-level mean distance (Spearman

ρ=0.98

) and recovers the same qualitative findings. We organize these comparisons through a measure-theoretic lens making their alignment and invariance assumptions explicit. We also establish an architecture-agnostic sufficient condition linking behavioral similarity to inference-prompt coverage, small excess population log-loss, and similar effective target distributions---a possible training-side account rather than an empirical explanation of the observed trends. Our pipeline is label-free, and re-encoding every response with three further encoders---down to one

73\times

smaller---preserves the rank geometry, the outliers, and the sign of the time trend.

Dong Qiao, Chris Ding, Jicong Fan

School of Data Science, The Chinese University of Hong Kong, Shenzhen, China

LLM Evaluation Representation Geometry in Language Models Drifting Models

Aug 11, 2026cond-mat.mtrl-sci

Chemically Meaningful Textualization Enables Explainable Validation of Metal-Organic Frameworks by Large Language Models

Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity. Existing validation approaches can identify non-computation-ready structures, but they often rely on heuristic rules, license requirement, or offer limited interpretability. Here, we show that large language models (LLMs) can serve as interpretable validators of MOF structures when crystallographic information is transformed into chemically meaningful text. By benchmarking nine descriptors, we find that successful LLM-based validation depends not on the amount of structural information alone, but on whether local coordination, framework connectivity, and chemical context are organized into a linguistically learnable representation. Fine-tuned LLMs using specialized descriptors (mof2text) achieve performance comparable to graph-based models in identifying unreasonable MOFs. Importantly, these models extend beyond black-box classification by generating diagnostic rationales for likely error sources, including abnormal bonding, connectivity, and charge states, as well as error-category predictions for annotated datasets. This work establishes chemically informed textualization as the key step that transforms LLMs from generic text models into practical and explainable tools for curating MOF databases.

Guobin Zhao, Xiao-Yan Li

Department of Chemistry, National University of Singapore, 3 Science Drive 3, Singapore 117543, Singapore

LLM Evaluation LLM Interpretability Materials Science Molecular Representation Learning

Aug 11, 2026cs.CL

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions. However, due to the lack of dedicated benchmarks, their capabilities remain poorly understood. To address this gap, we introduce SPIEval, a human-curated benchmark grounded in five cognitive capabilities (i.e., reasoning, disambiguation, integration, preference inference, and multi-intent decomposition). SPIEval comprises 250 tasks spanning 4,335 personal records distributed across 10 apps and supports multi-turn interaction through 21 tools. Analysis shows that the benchmark exhibits diverse scenarios, challenging tasks, scattered information, controllable environments, and verifiable outcomes. We evaluate nine representative LLMs and find substantial room for improvement. The best-performing model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, while the weakest achieves just 16.4%. Further analysis reveals that 79% of failures stem from inaccurate information localization, as LLMs often commit to plausible but incorrect information instead of continuing retrieval for verification. We also find that fewer than 2% of retrieval actions employ advanced search methods and observe substantial variation in search efficiency across models. These findings expose fundamental limitations of current LLM-based mobile assistants and motivate future research in this direction. Data and code are available at https://huggingface.co/datasets/Junjie-Ye/SPIEval.

Junjie Ye, Zhuohui Sheng, Shaofan Liu +12

1Fudan University · 2Tencent Hunyuan Team

LLM Evaluation AI Agent Benchmarks Information Retrieval Tool Use

Aug 11, 2026cs.CL

Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases

As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community typically evaluates models using large, unstructured benchmarks. While effective for general capabilities, these datasets fundamentally conflate causal mechanisms: even when an aggregate bias is detected, unstructured evaluations cannot disentangle whether it stems from baseline traits, contextual confounders, or complex interactions. To address this, we introduce an analytically exact framework for the controlled behavioral evaluation of LLMs. We bridge human psychometrics with LLM mechanics by resolving gaps in design, measurement, and analysis. First, we replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects. Second, we eliminate Monte Carlo text sampling noise by operating directly on exact, token-level Probability Mass Functions (PMFs). Third, we derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically. We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.

Davood Wadi, Mohsen Ghodrat, Matthew Philp

McGill University · University Canada West · Marketing Management +1

LLM Evaluation Cultural Bias in Language Models Language Model Bias Evaluation Causal Interventions in Language Models

Aug 11, 2026cs.CL

From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models

Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains. This progress primarily reflects reasoning depth. A complementary and comparatively unexamined capability is reasoning breadth: exploring multiple semantic directions in parallel and integrating the resulting clues into one coherent answer. We introduce MPAR-Bench, a bilingual English-Chinese benchmark that isolates reasoning breadth through multi-point associative reasoning. Inspired by the cooperative game Just One, each item asks a model to recover a hidden target from several independently generated, semantically diverse clues. We construct 1,000 items using a multi-agent clue-generation pipeline, embedding-based diversity filtering, and human verification. Only the answer space is drawn from public word lists, whereas every clue set is generated from scratch. Beyond exact-match accuracy, we evaluate models using accuracy, ANLS, embedding similarity, reasoning-trace verification, and four perturbations: clue masking, order shuffling, distractor injection, and multi-step clues. Across evaluated models, perturbations reduce accuracy by 9-18 percentage points in English and 5-12 percentage points in Chinese. Thinking mode improves standard-setting accuracy, especially in English, but does not consistently reduce sensitivity to perturbations. Case-level analysis also shows that extended reasoning can overturn an initially correct hypothesis. These results indicate that greater reasoning depth does not automatically confer robust reasoning breadth, and that reasoning breadth remains largely uncovered by current benchmarks.

Si'an Xie, Jiaxun Liu, Biao Yang +4

Beijing University of Posts and Telecommunications · Peking University · Kuaishou Technology

LLM Evaluation Multi-Hop Reasoning

Aug 11, 2026cs.CL

How Robust Are LLMs to Vietnamese Dialects?

Large Language Models (LLMs) are typically evaluated on standard written Vietnamese, yet everyday communication frequently involves regional dialects that preserve meaning but differ in surface form. Existing Vietnamese dialect work largely addresses this issue through dialect-to-standard normalization instead of measuring how the model fails under Vietnamese dialectal inputs. To address this gap, we present the first systematic evaluation of LLM robustness to Vietnamese dialect variation across multiple tasks, quantifying performance degradation and failure patterns. We introduce VialectBench (Vietnamese Dialects Benchmarking), a controlled benchmark for testing whether model decisions remain stable across six Vietnamese dialect groups. VialectBench contains 400 Standard Vietnamese source instances and 2,400 human-written dialectal rewrites spanning emotion recognition (ER), natural language inference (NLI), question answering (QA), and multiple-choice question answering (MCQA). Dataset evaluation with a fixed reference language model shows that the dialectal rewrites induce a measurable model-relative likelihood shift while remaining nearly equal in length to their Standard counterparts. Across ten instruction-tuned models, dialectal inputs reduce average performance by 2.82%, and no evaluated model is fully dialect-invariant. All four tasks are affected, with QA showing the largest average degradation. Robustness also varies substantially across dialect groups: PNT3 and PNT2 cause the largest average performance drops, at 6.17% and 4.73%, respectively, whereas PNB slightly improves average performance by 0.42%. The Central dialect group (PNT1-PNT4) also yields the highest average harmful-flip rate across all models, at 6.54%. These findings show that strong performance on Standard Vietnamese does not guarantee reliable behavior under meaning-preserving regional variation.

Minh Tran, Trinh Chau, Thanh-Nhan Le +4

University of Science, VNU-HCM · VNU University of Engineering and Technology · New York University Abu Dhabi +4

LLM Evaluation Language Model Robustness

Aug 11, 2026cs.IR

Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation

Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assessor framing affects judgment reliability and downstream system comparison. We study persona conditioning as a diagnostic mechanism for exposing LLM assessor sensitivity. Using task-oriented personas drawn from two complementary sources (PersonaHub and NVIDIA Nemotron-Personas-USA), we instantiate five assessor roles emphasizing intent interpretation, domain expertise, contrastive judgment, evidence verification, and global search-quality assessment, compared with a standard UMBRELA baseline. Across six LLM backbones on TREC DL20 and RAG24, our analyses reveal structured rather than uniform assessor sensitivity. Judgments usually remain close to the baseline while shifting assessment strictness, evidential threshold, or interpretation emphasis rather than producing widespread relevance reversals. At the system level, high-capacity models preserve system-ranking agreement, while smaller models amplify persona-induced instability. Local rank-displacement analysis shows sensitivity concentrates on particular retrieval systems and system types, especially neural ranking/reranking systems on DL20 and RAG-oriented pipelines on RAG24. Persona source matters less than assessor role and model capacity. These findings position persona-conditioned judging as a controlled sensitivity probe for stress-testing LLM-based IR evaluation pipelines and identifying systems whose evaluation outcomes are sensitive to assessor framing.

Samaneh Mohtadi, Pietro Bernardelle, Joel Mackenzie +1

The University of Queensland · Brisbane, Australia

LLM Evaluation LLM-as-a-Judge Language Model Bias Evaluation IR Evaluation

Aug 10, 2026cs.CL

Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility

Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern matching. We identify cross-contextual consistency as an underutilized behavioral property of LLMs: a credible answer should remain stable when the same task is placed under topic-aligned, content-neutral contextual variation. Building on this intuition, we operationalize Cross-Contextual Consistency (C3) by comparing model generations under original and perturbed prompts. Across 26 models and six benchmarks spanning reasoning, factuality, and code generation, we find that answers with smaller cross-contextual shifts are more likely to be correct or factual. We demonstrate that C3 provides a complementary axis of evaluation and can serve as a benchmark usefulness diagnostic, identifying which portions of a benchmark remain informative even when aggregated scores are widely considered "saturate".

Siyang Wu, Yibo Jiang, Bryon Aragam

Data Science Institute University of Chicago Chicago, USA · Department of Computer Science University of Chicago Chicago, USA · Booth School of Business University of Chicago Chicago, USA

Prompt Sensitivity LLM Evaluation Language Model Generation Evaluation Reasoning Consistency in Language Models LLM Reliability Cross-Lingual Consistency in Language Models

Aug 10, 2026cs.LG

Toward Human Rights Benchmarking for LLMs: A Pilot Methodology

Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether they can reason correctly about human rights law. To this end, we report our efforts to develop a robust and scalable methodology for creating HumRightsBench: the first expert-validated, scenario-based benchmark for evaluating reasoning grounded in the obligation structure of international human rights law. We adapt the IRAC framework for legal reasoning to better suit the unique reasoning patterns of human rights work (substituting P, "proposing remedies," for C, "legal conclusion," yielding IRAP) to structure our evaluation heuristics. We also produce a pilot series of authentic scenarios designed to implicate the many dimensions of real-world human rights issues and annotated by human rights lawyers and professionals across the world. Ultimately, we find that model accuracy scores range considerably across legal reasoning tasks (overall model performance ranges from 0.339 to 0.577, task min-max ranges from 0.025 to 0.774), which strongly implies that HumRightsBench is a capable instrument for advancing this emerging subfield of AI evaluations science at a critical moment in its evolution.

Savannah Thais, Wm. Matthew Kennedy, Abhigyan Acherjee +3

Hunter College, New York, USA · Oxford Internet Institute, University of Oxford, UK · King’s College London, UK +2

LLM Evaluation Moral Reasoning in Language Models Legal Reasoning

Aug 10, 2026cs.MA

The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse

LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests largely on benchmarks for verifiable tasks (mathematics, coding, coordination games), yet many of these applications concern problems where no objectively correct answer exists and where decision quality instead depends on integrating pluralistic perspectives to find mutually acceptable solutions. We argue that LLM reasoning capacity on this class of problems cannot be fully inferred from verifiable-task benchmarks, and that procedural evaluations of LLM discourse (respectfulness, justification, engagement) are systematically insufficient. We apply the Deliberative Reason Index (DRI), a measure developed in political science and validated across citizen assemblies, as a tool for evaluating reliable group-level reasoning on pluralistic, non-verifiable problems. Synthesizing recent evidence across 1,980 five-agent LLM runs on 12 citizen-assembly topics across 11 frontier model configurations, we find that LLM groups produce discourse with procedural quality comparable to human deliberation, while gains in intersubjective consistency are small, topic-dependent, and concentrated on tractable rather than ethically contested questions. LLM groups exhibit roughly one-third the perspective diversity of human assemblies and reverse the human convergence pattern: human deliberation decreases dispersion as diverse views synthesise, whereas LLM deliberation increases it. Engineering diversity through persona prompting does not restore the human dynamic but inverts which component of deliberative reasoning is updated. Our conclusion is constraining rather than prohibitive: LLMs can function as tools supporting human reasoning on pluralistic problems, but current evidence does not license treating them as autonomous deliberative agents.

Maurice Flechtner

University of Zurich, Zurich, Switzerland · ETH Zurich, Zurich, Switzerland

LLM Evaluation Multi-Agent Debate Deliberative Democracy LLM Reasoning

Aug 10, 2026cs.CL

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch

Large language models are increasingly being deployed in governmental settings, yet few existing evaluation frameworks jointly reflect the values of public administration and the linguistic requirements of non-English contexts. We present the "Grip on LLMs" framework, a systematic evaluation suite for Dutch governmental use developed in collaboration with domain experts from a major Dutch municipal organisation. Through an advisory board process, user research, and a survey of the users of a civil-servant chatbot, we identify six evaluation dimensions (factuality, honesty, social bias, energy consumption, cost, and training data transparency) and operationalise them into a benchmark suite covering more than 30 multilingual and Dutch-specific models. Our results reveal that no single model excels across all dimensions, and that trade-offs are unavoidable: higher quality consistently comes at greater environmental impact and financial cost, while bias remains largely independent of both. We further find that factuality (whether a model answers correctly) and honesty (whether a model acknowledges what it does not know) are governed by distinct properties, with high factuality not implying high honesty. To make these findings actionable for non-technical audiences, we release a publicly accessible, user-friendly model overview designed for the full range of stakeholders involved in governmental LLM selection, from engineers to policymakers.

Laurens Samson, Iva Gornishka, Gossa Lô +2

City of Amsterdam · Socially Intelligent Artificial Systems Group, University of Amsterdam · Fundamental AI Lab, University of Technology Nuremberg

Multilingual Language Model Evaluation LLM Evaluation Social Bias in Language Models Factual Knowledge in Language Models