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 1,643

May 9, 2026cs.CL

EdgeFlowerTune: Evaluating Federated LLM Fine-Tuning Under Realistic Edge System Constraints

Federated fine-tuning offers a promising paradigm for adapting large language models (LLMs) on edge devices by leveraging the rich, diverse, and continuously generated data from smartphones and IoT devices without compromising user data privacy. Such edge-side adaptation can improve model personalization, robustness, and responsiveness to local contexts. However, the practical feasibility of federated LLM fine-tuning on real edge devices remains unclear, as most existing work focuses on cross-silo or simulation-based settings, overlooking the resource and runtime constraints that determine whether a method is deployable on real edge systems. We present EdgeFlowerTune, a deployment-oriented benchmark for federated LLM fine-tuning under realistic edge-system constraints. EdgeFlowerTune jointly evaluates model quality and system costs, including communication, wall-clock latency, memory usage, energy consumption, and robustness to dynamic edge conditions. To compare methods in terms of effectiveness, efficiency, and robustness, EdgeFlowerTune introduces three complementary protocols: Quality-under-Budget, Cost-to-Target, and Robustness. We instantiate EdgeFlowerTune as a real-device platform built on Flower and MobileFineTuner, spanning commercial Android smartphones and NVIDIA edge development boards. Our benchmark results show that accuracy-only evaluation can lead to misleading conclusions: methods with similar final quality may differ substantially in deployability once realistic system constraints are considered. EdgeFlowerTune provides a reproducible benchmark for system-aware evaluation of federated LLM fine-tuning at the edge.

Jiaxiang Geng, Yiyi Lu, Lunyu Zhao +3

Duke Kunshan University · Flower Labs · University of Cambridge

LLM Evaluation LLM Fine-Tuning Edge ML Federated Fine-Tuning Federated Learning

May 9, 2026cs.AI

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules

Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce \ours{}, a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0%) confirms \ours{} requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \ours{},Pro exposes brittleness, with every model losing 13--60% relative accuracy under distractor expansion. \ours{},Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.

Devin Yasith De Silva, Dhaval Patel, Christodoulos Constantinides +7

2Rensselaer Polytechnic Institute · 1IBM · 3Independent Contributor

Logical Reasoning LLM Evaluation Predictive Maintenance Symbolic Reasoning Language Model Robustness

May 8, 2026cs.AI

Evaluating Developmental Cognition Capabilities of LLMs

Conversational AI is increasingly personalized around users' preferences, histories, goals, and knowledge, but much less around how users interpret and take up model outputs to construct and understand their reality. We draw on Robert Kegan's constructive-developmental theory as a complementary lens on this dimension. Existing methods for assessing developmental stage in the Keganian tradition rely either on expert interviews that do not scale or on sentence-completion instruments that are proprietary, lengthy, or invasive. To make this perspective tractable for LLM evaluation, we introduce the Developmental Sentence Completion Test (DSCT), a 20-item instrument designed to elicit developmental signal in self-administered text. Throughout, we treat the resulting labels as characterizations of stage-like structure in elicited responses, not as validated person-level developmental stage. We then ask how much of that signal can be recovered by LLMs across three elicited response regimes: simulated personas, real human respondents, and default model-generated answers. On simulated personas, top frontier models recover simulator-intended labels with high accuracy. On real human DSCT responses, human-LLM agreement is fair, with much stronger within-neighborhood than exact agreement. Finally, when LLMs answer DSCT prompts without persona-conditioning, their responses exhibit stable stage-like differences across model families, with larger and newer models tending to generate higher-rated text. These results suggest that stage-conditioned signal is cleaner in synthetic responses than in human-written DSCT text, and that the core constraint for stage-aware conversational AI is not classifier accuracy alone, but the availability of developmental signal from elicited text.

Xiao Xiao, Hayoun Noh, Mar Gonzalez-Franco

De Vinci Research Center, France · University of Oxford, UK · Google, USA

May 8, 2026cs.CL

Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation

The evaluation of Large Language Models (LLMs) faces a critical challenge in construct validity, where fragmented benchmarks and ad hoc metrics frequently conflate method variance, such as prompt sensitivity, with true latent capabilities. Concurrently, emerging research suggests that LLM capabilities and outputs can be modeled as continuous geometric manifolds. In this Systematization of Knowledge (SoK), we bridge these paradigms by proposing a generalized Multi-Trait Multi-Method (MTMM) framework for LLM evaluation. We formalize and unify nine evaluation metrics, including Paraphrase Instability, Drift Score, Overton Width, and Pluralism Score, interpreting them not as isolated scalar values but as geometric measurements within a shared latent coordinate space. This spatial unification factorizes model behavior into three orthogonal latent dimensions: (1) Instability and Sensitivity, (2) Position and Alignment, and (3) Coverage and Expressiveness. By systematically separating task-irrelevant perturbations from true capability spans, the framework provides a theoretically grounded and domain-agnostic taxonomy for robust and empirically stable benchmark design.

Adib Sakhawat, Tahsin Islam, Takia Farhin +3

Systems and Software Lab (SSL) Department of Computer Science and Engineering Islamic University of Technology, Dhaka, Bangladesh

LLM Evaluation Language Model Robustness

May 8, 2026cs.LG

CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs

Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a benchmark that evaluates generated CUDA against end-to-end human-expert SOTA systems. It spans single kernels, module-level operators, full applications, and unsolved challenge tasks across Ampere, Hopper, and Blackwell GPUs, with end-to-end tasks gated by domain-specific semantic validators. Evaluating models such as Claude-Opus-4.6 and GPT-5.4 shows a large gap between runnable CUDA and expert CUDA engineering: models often compile and pass tests, but rarely recover the optimization strategies needed to match expert performance. Application semantics further reduce success, and iterative or tool-augmented feedback can improve correctness while drifting toward slow fallback implementations. These results show that automated CUDA programming remains far from fully solved and requires stronger hardware reasoning, better tool use, and training objectives that connect code understanding to hardware architecture-grounded intelligence.

Shiyang Li, Zijian Zhang, Guangyan Sun +5

University of Minnesota · Northeastern University

LLM Evaluation GPU Kernel Optimization GPU Acceleration High-Performance Computing Large Language Model-Guided Optimization Code Generation+1

May 8, 2026cs.CL

Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment

Hallucination remains a persistent challenge in Large Language Models (LLMs), particularly in context-grounded settings such as RAG and agentic AI systems. This study focuses on contextual hallucination detection in summarization tasks. We analyze the QAGS-C and SummEval datasets by comparing original benchmark annotations with reason and span-based predictions from Gemini 2.5 Flash and GPT-5 Mini. To address systematic divergences between human labels and LLM judgments, we re-evaluated all conflicted samples through a human adjudication process involving 2 cross-cultural adjudicators. Following this re-evaluation, triple agreement (between human, GPT, and Gemini) increased by 6.38% for QAGS-C and 7.62% for SummEval. Similarly, model accuracy improved, with GPT increasing by 4.25% on QAGS-C and 2.34% on SummEval, while Gemini showed gains of 8.51% and 3.80%, respectively. Notably, adjudicators frequently sided with the models' judgments over original human annotations when LLMs provided explicit reasoning. Overall human adjudicator agreement ranged between 83% and 87%. These findings suggest that for ambiguity-prone tasks, single-pass annotations may be insufficient, and model-assisted re-evaluation yields more reliable benchmarks.

I. F. Atasoy, B. Mutlu, E. A. Sezer +1

Department of Computer Engineering, Hacettepe University, Ankara, 06800, Türkiye · Department of Computer Engineering, Ankara University, Ankara, 06830, Türkiye · Zephlen AI and Information Technologies Inc., Kocaeli, 41400, Türkiye

LLM Evaluation LLM-Assisted Annotation Human-in-the-Loop Evaluation LLM Hallucination Detection

May 8, 2026cs.LG

CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging

Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of GPU usage across scientific computing, machine learning, graphics, and systems workloads, CUDA debugging has become more challenging than ever. Current evaluations of LLM-based CUDA programming largely miss this setting: a model can pass correctness tests with repair by degeneration, simplifying the CUDA code into a safer but slower program that abandons the original optimization structure. We introduce CUDABEAVER, a benchmark for CUDA debugging from real failing workspaces produced during LLM-based CUDA generation. Each task provides the broken candidate, native build/test commands, raw error evidence, and a single editable file. CUDABEAVER evaluates whether a fixer truly repairs the failing CUDA code or merely finds a slower test-passing replacement, reporting results by failure category, debugging trajectory, stagnation mode, and performance preservation. We further propose pass@k(M,C,A), a protocol-conditional CUDA debugging metric by making the fixer M, corpus C, and protocol axes Aexplicit. Using this metric across 213 tasks and seven frontier LLMs, we show that protocol-aware evaluation gives a more faithful view of CUDA debugging ability: when performance-loss tolerance is high, fixers appear much stronger, but even a minor stricter performance requirement can sharply reduce measured success, shifting scores by up to 40 percentage points.

Shiyang Li, Haoyang Chen, Mattia Fazzini +1

University of Minnesota

LLM Evaluation Automated Program Repair

May 8, 2026cs.CL

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks

Existing benchmarks for legal AI focus primarily on tasks where LLMs must produce legal arguments or documents, yet the capacity to \emph{judge} such arguments -- weighing competing claims, applying doctrine to facts, and rendering reasoned decisions -- is arguably as fundamental to a well-functioning legal system as advocacy itself. We introduce Magis-Bench, a benchmark for evaluating LLMs on magistrate-level writing tasks derived from recent Brazilian competitive examinations for judicial positions. Magis-Bench comprises 74 questions from eight examinations conducted between 2023 and 2025, including discursive legal analysis questions with multi-turn structure and practical exercises requiring the composition of complete civil and criminal judicial sentences. We evaluate 23 state-of-the-art LLMs using an LLM-as-a-judge methodology with four independent frontier models as evaluators. Our results show strong inter-judge agreement (Kendall's

W = 0.984

; pairwise Kendall's

τ\ge 0.897

), with Google's Gemini-3-Pro-Preview achieving the highest average score (6.97/10), followed by Gemini-3-Flash-Preview (6.67) and Claude-4.5-Opus (6.46). Even the best-performing models score below 70% of the maximum, indicating that judicial-level legal reasoning and writing remain challenging for current LLMs. We release the complete benchmark, model outputs, and evaluation code to support further research on legal AI capabilities.

Ramon Pires, Thales Sales Almeida, Celio Larcher Junior +6

Maritaca AI Campinas, São Paulo, Brazil · Jusbrasil Salvador, Bahia, Brazil

Legal NLP LLM Evaluation Legal Reasoning

May 8, 2026cs.CL

A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering

Calibration measures whether a model's predicted confidence aligns with its empirical accuracy, and is central to the reliable deployment of large language models (LLMs) in high-stakes domains such as medicine and law. While much recent work focuses on improving LLM calibration, the equally important question of how to evaluate it in realistic settings remains underdeveloped. Open-ended question answering (QA), the most common deployment setting for modern LLMs, is where existing evaluation methods fall short: logit-based metrics need restricted output formats and internal probabilities; verbalized confidence is self-reported and often overconfident; and sampling-based methods rely on task-specific extraction rules without a clear finite-sample target. We introduce Sem-ECE (Semantic-Sampling Expected Calibration Error), a calibration evaluation framework for open-ended QA that samples answers from the model, groups them into semantic classes, and uses the resulting frequencies as confidence. We study two estimators within this framework: Sem

_1

-ECE, the same-sample self-consistency score, and Sem

_2

-ECE, a held-out variant that separates answer selection from confidence evaluation. We prove both are asymptotically unbiased, and further show that they agree on easy questions but diverge on hard ones with Sem

_2

achieving strictly smaller calibration error, so their gap also serves as a diagnostic for question difficulty. Experiments on three open-ended QA benchmarks across five leading commercial LLMs match our theoretical predictions and show that Sem-ECE outperforms verbalized confidence and existing sampling-based methods, while complementing logit-based evaluation when internal probabilities are unavailable.

Zhanliang Wang, Jiancong Xiao, Ruochen Jin +3

University of Pennsylvania, Philadelphia, PA · Dartmouth College, Hanover, NH

LLM Evaluation Confidence Estimation in Language Models Language Model Calibration Model Calibration LLM Reliability LLM Uncertainty Estimation

May 8, 2026cs.CL

Sanity Checks for Long-Form Hallucination Detection

Hallucination detection methods for large language models increasingly operate on chain-of-thought reasoning traces, yet it remains unclear whether they evaluate the reasoning itself or merely exploit surface correlates of the final answer. We introduce a controlled-invariance methodology that exposes this distinction through two oracle tests: \textsc{Force}, which replaces each response's final answer with the ground truth while preserving the reasoning trace, and \textsc{Remove}, which strips answer-announcement steps while leaving the trajectory intact. This reveals if their predictive power derives from answer-level artifacts rather than from the structure or validity of intermediate reasoning. We further show that once these artifacts are controlled for, effective detection does not necessarily require complex learned representations: TRACT, a lightweight scorer built on lexical trajectory features (hedging trends, step-length dynamics, and cross-response vocabulary convergence), achieves strong robustness while remaining competitive with or outperforming existing baselines on unperturbed traces. These findings suggest that the current central challenge in reasoning-aware hallucination detection is not the absence of signal in the trace, but the failure to isolate it from endpoint cues.

Geigh Zollicoffer, Minh Vu, Hongli Zhan +2

Los Alamos National Laboratory · The University of Texas at Austin · University of British Columbia

LLM Evaluation Hallucination Detection Hallucination in Language Models LLM Reliability LLM Hallucination Detection Reasoning Trace Analysis

May 8, 2026cs.LG

Augmenting Human Evaluation with LLM Judges: How Many Human Reviews Do You Need?

Large language models (LLMs) are increasingly used as automated evaluators of AI systems, including in high-stakes applications. In this role, LLMs are used to generate judgments about the quality, appropriateness, or even safety of model outputs. This approach is motivated by practical constraints. Expert human ratings are costly and difficult to scale, whereas LLM ratings can be produced quickly at low cost. However, current approaches to deploying LLM evaluators are ad hoc, typically limited to reporting agreement metrics between human and LLM judges as a justification for substitution of human ratings, and lack a formal basis for study design. This paper (1) shifts the role of the LLM judge from substitutive to auxiliary, and (2) formulates the LLM-as-a-judge paradigm as one of augmenting human evaluation through a two-stage sampling design, where LLM evaluations are measured for all observations at the first stage and human ratings are partially observed for a subsample at the second stage. We propose to use a doubly robust estimator from the missing data literature, which takes advantage of the robustness property against the prediction model, since the missingness model is known by design. Using the asymptotic variance of this estimator, we propose how sample sizes of human and LLM ratings can be determined to achieve a targeted level of power. We also show that a study can be efficiently designed by allocating more human ratings for types of evaluations where the predictability of LLM ratings is not high. To the best of our knowledge, there is very little guidance on how much human oversight should be retained when validating benchmarks.

Jane Paik Kim

Department of Psychiatry and Behavioral Sciences Stanford University Stanford, CA 94304

LLM Evaluation LLM-as-a-Judge Human-in-the-Loop Evaluation Doubly Robust Estimation

May 8, 2026cs.CL

CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers

Despite the rapid development of AI reviewers, evaluating such systems remains challenging: metrics favor overlap with human reviews over correctness. However, since human reviews often cover only a subset of salient issues and sometimes contain mistakes, they are unreliable as gold references. To address this, we build category-specific benchmark subsets and skip evaluation when the corresponding human reviews are missing to strengthen Completeness. We also leverage reviewer--author--meta-review discussions as expert annotations and filter unreliable reviews accordingly to strengthen Correctness. Finally, we introduce CoCoReviewBench, which curates 3,900 papers from ICLR and NeurIPS to enable reliable and fine-grained evaluation of AI reviewers. Analysis shows that AI reviewers remain limited in correctness and are prone to hallucinations, and highlights reasoning models as more effective reviewers, motivating further directions for improving AI reviewers. Benchmarks and models are available at https://github.com/hexuandeng/CoCoReviewBench.

Hexuan Deng, Xiaopeng Ke, Yichen Li +6

Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Zhongguancun Academy, Beijing, China · Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China +2

LLM Evaluation Automated Peer Review

May 8, 2026cs.CL

Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs

Large Language Models (LLMs) are increasingly used in settings where reliable self-assessment is critical. Assessing model reliability has evolved from using probabilistic correctness estimates to, more recently, eliciting verbalized confidence. Confidence, however, has been shown to be an inconsistent and overoptimistic predictor of model correctness. Drawing on cognitive appraisal theory, a framework from human psychology that decomposes self-evaluation into multiple components, we propose a multidimensional perspective on model self-assessment. We elicit six appraisal-based dimensions of self-assessment, alongside confidence, and evaluate their utility for predicting model failure across 12 LLMs and 38 tasks spanning eight domains. We find that competence-related appraisal dimensions, particularly effort and ability, consistently match or outperform confidence across most settings. Effort additionally yields less overoptimistic estimates that remain stable across model sizes. In contrast, affective dimensions provide marginally predictive signals. Furthermore, the most informative dimension varies systematically with task characteristics: effort is most predictive for reasoning-intensive tasks, while ability and confidence dominate on retrieval-oriented tasks. Broadly, our findings indicate that structured multidimensional self-assessment is a promising approach to improving the reliability and safety of language model deployment across diverse real-world settings.

Sree Bhattacharyya, Samarth Khanna, Leona Chen +3

Department of Informatics and Intelligent Systems, College of Information Sciences, The Pennsylvania State University. · Department of Computer Science and Engineering, College of Engineering, The Pennsylvania State University.

LLM Evaluation Confidence Estimation in Language Models Language Model Self-Assessment Language Model Calibration LLM Reliability LLM Uncertainty Estimation

May 8, 2026cs.LG

Tracing Uncertainty in Language Model "Reasoning"

Language model (LM) "reasoning", commonly described as Chain-of-Thought or test-time scaling, often improves benchmark performance, but the dynamics underlying this process remain poorly understood. We study these dynamics through the lens of uncertainty quantification by treating the "reasoning" traces, the intermediate token sequences generated by LMs, as evolving model states. We summarize each trace by an uncertainty trace profile: a small set of features describing the shape of the uncertainty signal over its trace, such as its slope and linearity. We find that across five LMs evaluated on GSM8K and ProntoQA, these profiles predict whether a trace yields a correct final answer with AUROC up to 0.807, improving markedly on recent related work. We reach AUROC 0.801 using only the first few hundred tokens of full traces, suggesting that errors can be detected early in the generation. A detailed comparison of correct and incorrect traces further reveals qualitatively distinct uncertainty profiles, with correct traces showing a steeper and less linear decline in uncertainty. Together, the results suggest that our method, grounded in decision-making under uncertainty, provides a principled lens for studying the generative process underlying LM "reasoning".

Nils Grünefeld, Bertram Højer, Philipp Mondorf +5

Data Science Section, IT University of Copenhagen · Pioneer Centre for Artificial Intelligence · MaiNLP, Center for Information and Language Processing, LMU Munich +2

LLM Evaluation CoT Reasoning LLM Uncertainty Estimation Reasoning Trace Analysis

May 8, 2026cs.CL

Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs

This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE) model with 3B active parameters. Performance is investigated across a wide variety of representative benchmarks, and is compared against comparably-sized open-source MoE and dense models. In comparison with popular Italian models, namely FastwebMIIA-7B, Minerva-7B, Velvet-14B, and LLaMAntino-3-ANITA-8B, EngGPT2MoE-16B-A3B performs as well or better on international benchmarks: ARC-Challenge, GSM8K, AIME24, AIME25, MMLU, and HumanEval (HE). It achieves the best performance for the longest context setting (32k) of the RULER benchmark. On the Italian benchmark dataset ITALIC, the model performs as well or better than the other models except for Velvet-14B, which outperforms it. Compared with popular MoE models of comparable size, the new model reports higher values than DeepSeek-MoE-16B-Chat on all considered benchmarks. It has higher values than Moonlight-16B-A3B on HE, MMLU, AIME24, AIME25, GSM8K, and the 32k RULER setting, but lower on BFCL and some ARC and ITALIC settings. Finally it has lower values than GPT-OSS-20B on most benchmarks, including HE, MMLU, AIME24, AIME25, GSM8K, ARC, BFCL, and the RULER 32k. When compared with popular dense models, EngGPT2MoE-16B-A3B reports higher values on AIME24 and AIME25 than Llama-3.1-8B-Instruct, Gemma-3-12b-it, and Ministral-3-8BInstruct-2512-BF16, but lower values on ITALIC, BFCL, and RULER with a 32k context. When performance is aggregated across all benchmark metrics, EngGPT2MoE-16B-A3B shows higher performance than the Italian models under evaluation while achieving lower results than some of the most performant international models, in particular GPT-5 nano and Qwen3-8B. Taken together, our findings find the new model to be a step forward for native Italian Large Language Models.

Andrea Sassella, Andrea Chizzola, Tommaso Bianchi +2

2DEIB, Politecnico di Milano · 1AIRIC, Politecnico di Milano

LLM Evaluation Mixture-of-Experts Language Models Open-Weight Language Models Language Modeling

May 8, 2026cs.AI

FactoryBench: Evaluating Industrial Machine Understanding

We introduce FactoryBench, a benchmark for evaluating time-series models and LLMs on machine understanding over industrial robotic telemetry. Q&A pairs are organized along four causal levels (state, intervention, counterfactual, decision) instantiating Pearl's ladder of causation, and span five answer formats: four structured formats are scored deterministically and free-form answers are scored by an LLM-as-judge voting protocol. We propose a scalable Q&A generation framework built around structured question templates, present FactoryWave (a dense, multitask, multivariate sensor dataset collected from a UR3 cobot and a KUKA KR10 industrial arm), and construct FactoryBench as a large-scale benchmark of over 70k Q&A items grounded in roughly 15k normalized episodes from FactoryWave, AURSAD, and voraus-AD. Zero-shot evaluation of six frontier LLMs shows that no model exceeds 50% on structured levels or 18% on decision-making, revealing a wide gap between current models and operational machine understanding.

Yanis Merzouki, Coral Izquierdo, Matei Ignuta-Ciuncanu +8

1ETH Zurich · 2Forgis · 3UC3M +4

Manufacturing LLM Evaluation Robotics Causal Reasoning Industrial Robotics

May 8, 2026cs.CL

Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation

Automated short answer scoring (ASAS) is shifting from discriminative, fine-tuned models to large language models (LLMs) used in few-shot settings. This paradigm leverages LLMs broad world knowledge and ease of deployment, but limited task-specific data may reduce alignment on complex scoring tasks. In particular, its impact on scoring partially correct responses that require nuanced interpretation remains underexplored. We investigate the relationship between the degree of task-specific adaptation of different models and quality-conditioned scoring agreement. We compare three LLMs (GPT-5.2, GPT-4o, Claude Opus 4.5) in few-shot mode, a fine-tuned BERT-based encoder, and a human expert on two open-ended biology items, using several hundred student responses and ground truth scores provided by a biology education expert. The results show that human-human agreement is highest and stable across the full quality spectrum. All AI models perform well on fully correct and fully incorrect responses, but exhibit substantial degradation on mid-range responses. This mid-range degradation is conditioned on task-specific adaptation: It is most severe in few-shot LLMs with few examples and decreases as task-specific data increases, with fine-tuned encoder models performing best. This mid-range degradation may lead to inequitable evaluation of responses produced by students with developing understanding. Our findings highlight the importance of quality-conditioned fairness, with particular attention to mid-range responses.

Abigail Victoria Gurin Schleifer, Moriah Ariely, Beata Beigman Klebanov +2

Weizmann Institute of Science, Rehovot, Israel · ETS, Princeton, USA

LLM Evaluation AI in Education Few-Shot Learning Automated Grading

May 8, 2026cs.CL

Multi-Dimensional Evaluation of LLMs for Grammatical Error Correction

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack comprehensive evaluation on grammar correction tasks; (2) whether combining these LLMs improves correction quality is unexplored; and (3) the extent to which reference-based metrics underestimate GEC system performance has not been adequately quantified. In this study, first, we evaluate latest-generation LLMs on edit precision, fluency preservation, and meaning retention, showing fine-tuned GPT-4o achieves state-of-the-art performance across all three dimensions. Second, through grammatical error type analysis we demonstrate that individual LLMs exhibit highly similar error correction patterns (

ρ=0.947

). Third, we show that reference-based metrics underestimate GEC performance with 73.76% of GPT-4o corrections different from gold standards being equally valid or even superior. These GEC evaluation findings equip educators with guidance for selecting GEC assistants that enhance rather than constrain student linguistic development. We make our data, code, and models publicly available.

Adnan Labib, Qiao Wang, Yixuan Huang +1

King’s College London, London, United Kingdom · Hosei University, Tokyo, Japan · Waseda University, Tokyo, Japan +1

LLM Evaluation Grammatical Error Correction Automated Evaluation

May 8, 2026cs.CL

Post-training makes large language models less human-like

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.

Marcel Binz, Elif Akata, Abdullah Almaatouq +76

LLM Evaluation LLM Alignment Human Behavior Prediction Language Model Post-Training Persona-Conditioned Generation

May 8, 2026cs.CL

Position: The Term "Machine Unlearning" Is Overused in LLMs

Large language models increasingly face demands to "forget" training data, knowledge, or behaviors due to regulatory deletion obligations, copyright/licensing disputes, and safety or product-policy requirements. This position paper argues that machine unlearning is overused as a term in LLM research and should be reserved for dataset-defined deletion: removing the training influence of a precisely specified forget set such that the resulting model is approximately indistinguishable from retraining without that data. We contend that many tasks currently labeled "unlearning" (e.g., refusal for harmful requests, entity/knowledge removal, or targeted suppression) pursue different, often policy-dependent objectives and therefore require different terminology and baselines (e.g., alignment, suppression, editing, obfuscation). We further argue that this confusion is not cosmetic: because papers make different implicit guarantees under the same label, metrics and benchmarks are frequently reused outside their intended scope, rewarding surface-level non-disclosure (e.g., low ROUGE/forget accuracy) even when retraining-equivalence is not tested and derived capabilities remain. We conclude by calling for stricter terminology tied to explicit guarantees and reference models, and for evaluations that match the claimed objective.

Sangyeon Yoon, Yeachan Jun, Albert No

Department of Artificial Intelligence, Yonsei University, Seoul, Korea.

LLM Evaluation Machine Unlearning LLM Unlearning

May 8, 2026cs.SE

Prompt Engineering Strategies for LLM-based Qualitative Coding of Psychological Safety in Software Engineering Communities: A Controlled Empirical Study

Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding process shaped by the subjective interpretation of individual researchers and sensitive to methodological choices such as prompt design. Recent advancements in Large Language Models (LLMs) offer promising opportunities to support this type of analysis, although their reliability in reproducing human qualitative reasoning under varying prompting conditions remains largely untested. This study presents a controlled empirical evaluation of three LLMs -- Claude Haiku, DeepSeek-Chat, and Gemini 2.5 Flash -- across two prompt engineering strategies (zero-shot and multi-shot closed coding), using Cohen's kappa as the primary agreement metric over ten independent runs per configuration. Results suggest that multi-shot prompting significantly improves agreement for Claude Haiku (Delta kappa = +0.034, Wilcoxon p = 0.004) but not for DeepSeek-Chat or Gemini 2.5 Flash. Intra-model stability varies substantially -- DeepSeek-Chat and Claude Haiku exhibit the lowest variance (SD approx. 0.017), while Gemini 2.5 Flash is the least stable (SD = 0.038). A systematic over-prediction of "Sharing Negative Feedback" is identified across all models (bias ratios up to 5.25x), alongside consistent under-prediction of "Expressing Concerns." Collectively, these findings provide empirical evidence for prompt engineering guidelines in LLM-assisted qualitative coding for software engineering research.

Moaath Alshaikh, Tasneem Alshaher, Ricardo Vieira +7

Federal University of Bahia · State University of Feira de Santana · Federal University of Sergipe +1

Software Engineering LLM Evaluation LLM Prompting LLM-Assisted Annotation Language Model Bias Evaluation

May 8, 2026cs.LG

Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts

Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routing headroom to an "unsolvability ceiling", queries no model in the pool can solve. We present a large-scale study of multi-tier LLM routing with 206,000 query-model pairs across six benchmarks (MMLU, MedQA, HumanEval, MBPP, Alpaca, ShareGPT) using the Gemma 4 and Llama 3.1 families. Evaluating with both LLM-as-a-judge and exact-match metrics, we show that a substantial portion of reported unsolvability stems from evaluation artifacts: (i) systematic judge biases favoring verbosity over correctness, (ii) truncation under fixed generation budgets, and (iii) output format mismatches. Through dual-judge validation and exact-match grounding, we reduce measured unsolvability across tasks. We introduce a decomposition framework attributing failures to these artifacts, revealing consistent patterns across domains and model families. These artifacts also distort router training signals: standard routers collapse to majority-class prediction (~79% smallest-tier optimal), confirmed via random-feature and shuffled-label controls, incurring a 13-17 percentage point opportunity cost. We provide actionable recommendations including dual-judge validation, exact-match anchoring, and cost-sensitive objectives. Our findings suggest existing routing headroom estimates are substantially inflated, underscoring the need for reliable evaluation protocols in multi-LLM systems.

Saloni Garg, Amit Sagtani

Independent Researcher San Francisco, California, USA · San Francisco State University San Francisco, California, USA

LLM Evaluation LLM-as-a-Judge LLM Routing

May 8, 2026cs.CL

From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs

Multiple-choice reasoning benchmarks face dual challenges: rapid saturation from advancing models and data contamination that undermines static evaluations. Ad-hoc hardening methods (paraphrasing, perturbation) attempt to increase difficulty but sacrifice logical validity for surface complexity, falling short to challenge advanced reasoning models. We present LogiHard, a formal framework that deterministically transforms 0-order selection into 2-order logical judgment, which significantly increases the thinking overhead and reasoning steps. The framework integrates Item Response Theory (IRT) for computerized adaptive testing (CAT), enabling precise difficulty control with fewer questions than static benchmarks. We instantiate LogiHard-2k, a logical reasoning dataset constructed by cognitively ranking high-stakes examination questions via 9-dimensional analysis of model thinking traces, followed by combinatorial transformation of high-difficulty items. Evaluation across twelve state-of-the-art models reveals an accuracy degradation ranging from 31% to 56% on combinatorially hardened questions. LLMs suffer from the multi-select failure and early exit bias, which are not shared by human testees. Zero-shot transfer to MMLU demonstrates 47% accuracy degradation (89.84% to 42.86%), confirming applicability across domains with provable validity preservation. The consistent aggregate degeneration is domain-agnostic and stems not from knowledge deficits but from a combinatorial reasoning gap, reflecting a training-induced completeness-verification deficit.

Hanmeng Liu, Shichao Weng, Xiulai Liu +3

Hainan University, Haikou, China · Fudan University, Shanghai, China

Logical Reasoning LLM Evaluation Educational Assessment LLM Reasoning

May 8, 2026cs.LG

FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution

Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult because the true impact of a new idea may take years to emerge. We address this challenge by using the impact forecasting of human-authored manuscripts as a verifiable proxy task. In a prospective forecasting study, we find that frontier LLMs fail to reliably distinguish high-impact papers from ordinary publications, suggesting that static text-based judging is insufficient for scientific evaluation. To address this limitation, we propose

\textbf{FAME}

(

\underline{\text{F}}

orecasting

\underline{\text{A}}

cademic Impact via Continuous-Time

\underline{\text{M}}

anifold

\underline{\text{E}}

volution), a spatiotemporal framework for modeling the dynamic trajectories of scientific topics. FAME projects papers into a dynamic latent space informed by textual features and a verified knowledge-flow graph, learning geometric constraints that align impactful manuscripts with the forward momentum of their fields. Experiments on 3,200 arXiv papers across three fast-evolving subfields show that FAME consistently and substantially outperforms state-of-the-art LLM evaluators in prospective multidimensional impact forecasting. Furthermore, integrating FAME's dynamic geometric signals into LLMs significantly improves their forecasting performance. These results support manuscript impact forecasting as a useful, measurable proxy benchmark and position FAME as a strong, trajectory-aware foundation for automated scientific evaluation.

Jianrong Ding, Jianyuan Zhong, Zhengyan Shi +1

Department of Computer Science and Engineering The Chinese University of Hong Kong

AI for Science LLM Evaluation Forecasting Benchmarks

May 8, 2026cs.CL

The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval

Existing Large Language Model (LLM) benchmarks primarily focus on syntactically correct inputs, leaving a significant gap in evaluation on imperfect text. In this work, we study how word-boundary corruption affects how LLMs detect targeted information. By inserting whitespace characters within words to break them into fragments, LLMs' detection accuracy follows a U-shaped curve with the increase in insertion rate. We refer to this curve as the Text Uncanny Valley. To explain such observation, we propose a mode transition hypothesis: LLMs operate in a word-level mode for near-normal text and a character-level mode for heavily fragmented text, with the valley marking the disordered transition where neither mode is effective. Four experiments and one analysis are consistent with this account: in-context learning fails to rescue valley-bottom performance; regularizing the perturbation substantially reduces the U-shape; a math reasoning task replicates the U-shape for Gemini 3.0 Flash but not for stronger models, suggesting the effect is attenuated when tasks rely less on exact lexical alignment; and tokenization entropy peaks before the F1 minimum, consistent with a regime-conflict interpretation. These findings reveal a failure mode invisible to clean-text benchmarks yet directly relevant to any deployment scenario involving noisy or uncurated text inputs.

Zekai Tong, Ruiyao Xu, Aryan Shrivastava +2

University of Chicago · 2Northwestern University

LLM Evaluation LLM Reliability LLM Information Extraction Language Model Robustness

May 8, 2026cs.LO

MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries

The ecosystem of Lean and Mathlib has become the de facto standard for large language model (LLM) assisted formal reasoning with remarkable successes in recent years. Those successes, however, only consume Mathlib as an essential dependency but do not directly contribute to it. In the meantime, the growth of Mathlib has recently been bottlenecked by the review process, which requires human reviewers to judge whether proposed pull requests (PRs) follow the Mathlib's conventions and are worth integrating as part of a shared mathematical infrastructure. This leads to our central question: can LLMs help review Mathlib PRs? To this end, we introduce MathlibPR, a benchmark built from real Mathlib4 PR histories. We further propose a staged evaluation protocol and use it to evaluate both LLM models (e.g., DeepSeek, Qwen, Goedel, and Kimina) and LLM agents (e.g., Codex and Claude Code). Surprisingly, both LLM models and LLM agents struggle to distinguish merge-ready PRs from build-passing PRs that were revised or never merged. By turning Mathlib PR histories into a supervised signal, MathlibPR provides a step toward reviewer assistants and reward models that could help evaluate PRs and steer LLMs toward producing merge-ready Mathlib contributions.

Zixuan Xie, Xinyu Liu, Shangtong Zhang

University of Virginia

LLM Evaluation LLM Agent Evaluation Automated Code Review

May 8, 2026cs.LG

The Position Curse: LLMs Struggle to Locate the Last Few Items in a List

Modern large language models (LLMs) can find a needle in a haystack (locating a single relevant fact buried among hundreds of thousands of irrelevant tokens) with near-saturated accuracy, yet fail to retrieve the last few items in a short list. We call this failure the Position Curse. For instance, even in a two-line code snippet, Claude Opus 4.6 misidentifies the second-to-last line most of the time. To characterize this failure, we evaluated two complementary queries: given a position in a sequence (of letters or words), retrieve the corresponding item; and given an item, return its position. Each position is specified as a forward or backward offset from an anchor, either an endpoint of the list (its start or end) or another item in the list. Across both open-source and frontier closed-source models, backward retrieval substantially lags forward retrieval. To test whether this capability can be rescued by post-training, we constructed PosBench, a position-focused training dataset. LoRA fine-tuning improves both forward and backward retrieval and generalizes to a held-out code-understanding benchmark (PyIndex), yet absolute performance remains far from saturated. As LLM coding agents increasingly operate over large codebases where precise indexing becomes essential for code understanding and editing, position-based retrieval emerges as a key capability for future pretraining objectives and model design.

Zhanqi Zhang, Hua-Dong Xiong, Robert C. Wilson +3

UC San Diego · Georgia Tech · New York University

LLM Evaluation LLM Fine-Tuning

May 8, 2026cs.CL

SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions

Evaluating literary quality requires assessing interpretive dimensions such as cultural representation, emotional depth, and philosophical sophistication that resist straightforward computational measurement. We introduce SAGE, a hierarchical evaluation framework that decomposes literary quality into ontology-grounded interpretive dimensions assessed through structured large language model evaluation with multi-round iterative reflection and independent validation. We validate the framework on 100 short stories (50 canonical works, 30 pulp fiction, 20 LLM-generated narratives) across three analytical layers (cultural, emotional-psychological, existential-philosophical) using dual-mode assessment. Across 600 evaluations, the framework achieves 98.8% score convergence and greater than 94% inter-rater agreement, with near-perfect mode invariance between content-based and metadata-based evaluation. Statistical analysis reveals a consistent genre hierarchy (Canonical > Pulp > LLM, all p<0.001) with layer-specific discrimination: cultural critique and philosophical depth exhibit very large effect sizes (Cohen's d>2.4), while emotional representation shows smaller gaps (d=1.68), suggesting that affective patterns are more learnable from training data than critical stance or philosophical depth. Cross-layer correlations (r=0.649-0.683) confirm the three dimensions capture empirically distinguishable quality facets. These findings demonstrate that theory-driven LLM evaluation can achieve measurement-grade reliability and support systematic identification of where current generative models fall short of human literary production, with direct implications for scalable automated evaluation of open-ended text generation.

Tianyu Wang, Nianjun Zhou

Mercy University, Math & Computer Science Department · Dobbs Ferry, NY, USA · IBM T.J. Watson Research Center +1

Computational Literary Studies LLM Evaluation LLM-as-a-Judge Automated Evaluation

May 8, 2026cs.CL

NSMQ Riddles: A Benchmark of Scientific and Mathematical Riddles for Quizzing Large Language Models

Large Language Models (LLMs) have shown good performance on various science educational benchmarks, demonstrating their potential for use in science and mathematics education. Yet, LLMs tend to be evaluated on science and mathematical educational datasets from the Western world, with an underrepresentation of datasets from the Global South. Furthermore, they tend to have multiple-choice answer options that are trivial to evaluate. In this work, we present NSMQ Riddles, a novel benchmark of Scientific and Mathematical Riddles from Ghana's National Science and Maths Quiz (NSMQ) competition to evaluate LLMs. The NSMQ is an annual live TV competition for senior secondary school students in Ghana that brings together the smartest high school students in Ghana who compete in teams of 2 by answering questions in biology, chemistry, physics, and math over five rounds and five stages until a winning team is crowned for that year. NSMQ Riddles consists of 11 years of riddle questions (n=1.8K) from the 5th round, with each riddle containing a minimum of 3 clues. Students compete to be the first to guess the answer on any of the clues, with earlier clues being vague and also fetching more points. The answers are usually a number, word, or short phrase, allowing for automatic evaluation. We evaluated state-of-the-art models: closed (GPT-5.4, Gemini 3.1 Pro, Claude Opus 4.6) and open models (Kimi-K2.5, DeepSeek-V3.1, GPT-OSS-120B) with high and low reasoning settings. Our evaluation shows that the dataset is challenging even for state-of-the-art LLMs, which performed worse than the best student contestants. This work contributes a novel and challenging benchmark for scientific and mathematical reasoning from the Global South towards enabling a true global benchmarking of LLMs' capabilities for science and mathematics education.

George Boateng, Naafi Ibrahim, Samuel John +8

ETH Zurich, Switzerland · Kwame AI Inc., U.S. · Ashesi University, Ghana +1

Mathematical Reasoning Benchmarks LLM Evaluation AI in Education Scientific QA

May 7, 2026stat.ML

An Interpretable and Scalable Framework for Evaluating Large Language Models

Evaluation of large language models (LLMs) is increasingly critical, yet standard benchmarking methods rely on average accuracy, overlooking both the inherent stochasticity of LLM outputs and the heterogeneity of benchmark items. Item Response Theory (IRT) offers a principled framework for modeling latent model abilities and item characteristics, but conventional methods are computationally expensive and numerically unstable, limiting large-scale implementations. To address these challenges, we propose an interpretable and scalable framework for LLM evaluation based on the majorization-minimization principle. Our approach reformulates the problem as a sequence of constrained matrix factorization subproblems, enabling stable and efficient parameter estimation with theoretical guarantees for identifiability and convergence. Experiments on synthetic and real-world datasets, including MATH-500 and six Open LLM Leaderboard benchmarks, demonstrate that our method achieves superior scalability and interpretability. It delivers orders-of-magnitude speedups over competing methods while maintaining comparable or even higher estimation accuracy. Our results align with established scaling laws and offer insights into item difficulty and discrimination, informing more principled benchmark design.

Xinhao Qu, Qiang Heng, Hao Zeng +1

Department of Statistics, University of California, Riverside · School of Statistics and Data Science, Southeast University · Department of Statistics and Data Science, Southern University of Science and Technology

LLM Evaluation Item Response Theory