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

Jul 29, 2026cs.AI

A dataset of rated conceptual arguments

Large language models have improved rapidly on tasks with verifiable answers, such as mathematics and programming. Much less is known about their ability to reason about what we call conceptual questions: questions for which no ground truth is realistically accessible and no widely accepted resolution methodology exists, but on which progress can still be made by debating arguments. Most philosophical questions are of this kind, as are central components of questions in AI safety, decision theory, and social choice. Our approach is based on the view that while bottom-line conclusions on such questions are hard to evaluate, individual contextualized arguments can be evaluated far more reliably. We therefore introduce a dataset of 951 argumentative critiques of 442 position texts, spanning topics from AI safety and decision theory to ethics and politics, with 1,458 ratings by six expert raters along dimensions including centrality, strength, correctness, and clarity. We propose two scoring functions and benchmark a range of models. Performance tracks general capability rankings.

Emery Cooper, Caspar Oesterheld, Linh Chi Nguyen +2

Jul 29, 2026cs.CL

Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints. We present a systematic zero-shot evaluation of 41 open-weight language models spanning 15 families and the 135M--9B parameter range across eight English single-label intent-classification datasets. A ninth dataset, ATIS, uses five labeled demonstrations and is reported as an auxiliary five-shot result. The evaluation includes standard benchmarks, a large-scale voice-assistant corpus, and production-derived e-commerce datasets. Beyond exact-match accuracy, we analyze confidence calibration, robustness to realistic input perturbations, statistical reliability of model rankings, deployment efficiency, and benchmark saturation. Our results show that instruction-tuned 3B models can outperform several evaluated 7B base models, that differences among leading models on MASSIVE are statistically indistinguishable under pairwise McNemar tests, and that widely used benchmarks such as SNIPS have become saturated and no longer meaningfully discriminate among current open-weight models. Instruction tuning's effect on confidence calibration is inconsistent rather than uniformly harmful. These findings provide practical guidance for selecting and evaluating open-weight language models for intent classification.

Parishruthi Ganesh, Gerry Dozier, Cheryl Seals

Department of Computer Science and Software Engineering Auburn University Auburn, Alabama, USA

LLM Evaluation Zero-Shot Text Classification Intent Classification Open-Weight Language Models Language Model Calibration Language Model Robustness

Jul 29, 2026cs.AI

Dimensionality and Measurement Precision in HLE's Multiple-Choice Subset

Humanity's Last Exam (HLE) is widely used to evaluate frontier language models. HLE organizes its questions into eight subject-domain categories, whose subscores are often interpreted as evidence of distinct capabilities. However, no study has assessed whether these labels correspond to empirically separable latent constructs, nor whether the benchmark effectively differentiates between models of similar ability. We evaluate 29 LLMs on the text-only multiple-choice subset of HLE (

J = 428

items) and apply psychometric methods to assess both the dimensionality of the benchmark and the distribution of its measurement precision. Fitting a two-parameter logistic IRT model, we find convergent evidence that HLE measures a single general reasoning factor: McDonald's

ω_h = 0.998

, domain labels explain only 3.5% of item response variance, within- and between-domain residual correlations are nearly identical (Cohen's

d = 0.016

), and domain-specific ability estimates are near-redundant with the total score (

r \geq 0.81

). A separate analysis of the test information function reveals that measurement precision concentrates at moderate ability levels and drops sharply above

θ= 0

, where frontier models sit. These findings suggest that HLE's domain subscores do not warrant distinct capability interpretations and that the benchmark's ability to discriminate among the strongest models is limited.

Mayank Sharma, Savira Nadela, Tyler Matteson

Stanford University

LLM Evaluation Psychometric Validation

Jul 29, 2026cs.CL

Benchmarking LLM Competence on Logical Inference over Probability Operators

Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty are necessary for not only everyday conversations but also for high-stakes domains such as medicine and law. While large language models are increasingly evaluated on logical reasoning tasks, disentangling principled, symbolic reasoning from clever surface-level pattern matching is fraught with difficulty. We introduce a benchmark for reasoning over probability operators--inference over sentences with gradable epistemic modals (e.g., probably, might, must) containing 14,320 procedurally-generated English prompts across fifteen inference templates, systematically varying question form, negation strategy, and surface content. Evaluating 29 models, we find that most show answer biases independent of the logical form, a systematic preference for Yes or No. We summarize this with a competence floor: the worse of a model's accuracy on Yes-correct and No-correct items. Only 9 of 29 models exceed random chance. We also test variations in question form, verb phrases/activity, and both the gender and origin of names used in the prompts, finding biases across every axis.

Nayera Hasan, Jack Greff, Alvin Grissom

Haverford College

Probabilistic Logic LLM Evaluation Language Model Bias Evaluation LLM Reasoning

Jul 29, 2026cs.CL

APEX-Accounting

We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved by experts in accounting and bookkeeping, who also wrote grading rubrics. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, ahead of Muse-Spark-1.1 (xHigh) at 52.6%. No model scores more than 2.6% Pass^8 (GPT-5.6-Sol (Max+Pro)) and the highest Pass@8 is 21.5% (Muse-Spark-1.1 (xHigh)). We experiment with increasing the token budget from

1 to

50 and observe an instance of Simpson's paradox: scores increase as the token budget increases but within a given budget-constrained harness, scores are lower on tasks where the model spends more tokens. As APEX-Accounting is a closed benchmark, leaderboard evals can be run for any frontier model on request.

Julien Benchek, Austin Bennett, Jasmin Kern +8

1Mercor · 2Ramp

LLM Evaluation Business Process Automation AI Agent Benchmarks

Jul 29, 2026cs.LG

BayesAME: Bayesian Active Model Evaluation

Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate full benchmark performance by evaluating models on only a subset of items, known as a coreset. Current literature mostly requires the practitioner to input a coreset size. However, when reliable performance estimation takes priority over efficiency, an evaluation method should also be capable of automatically determining a coreset size that reflects this priority. We introduce BayesAME, a sequential Bayesian framework specifically targeting automatic determination of the coreset size. BayesAME models performance as a random variable by defining a latent ability for each group of items sharing the same historical model performances, with a joint prior distribution encoding the belief that the target model behaves similarly to these historical models. The posterior distribution over these abilities is used to derive performance estimators, quantify performance uncertainty, and select items to add to the coreset via an information-gain criterion. The coreset is iteratively augmented until the performance estimate fluctuation and the performance uncertainty fall below their respective user-defined thresholds. We propose a multi-target extension that captures performance correlations across multiple target models to further reduce the coreset size. Through extensive experiments across diverse benchmarks, we demonstrate that BayesAME consistently outperforms sequential adaptations of existing methods. Crucially, our comprehensive analysis addresses recent skepticism in the literature, establishing that non-random coreset selection is advantageous over random selection. Finally, we highlight that leveraging continuous response log-likelihoods over traditional binary scores significantly enhances estimation accuracy.

Paula Cordero Encinar, Taylan Cemgil, Arnaud Doucet +2

Imperial College London (work conducted while at Google DeepMind) · Google DeepMind

LLM Evaluation Adaptive Sampling Coreset Selection Bayesian Experimental Design

Jul 29, 2026cs.CL

ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification. In this work, we propose ForgetBench, a benchmark designed to systematically characterize forgetting behavior in LLMs under continual knowledge editing. ForgetBench introduces two complementary evaluation paradigms, namely concept-based QA and scenario-based QA, to disentangle isolated factual retention from structured relational knowledge preservation. Building upon a sequential editing framework, we construct temporally ordered knowledge streams and evaluate model behavior across multiple editing stages. To quantitatively analyze long-term retention dynamics, we further introduce a unified evaluation framework that models knowledge evolution over time, enabling the measurement of temporal decay, retention strength, and cross-instance stability. Extensive experiments across diverse models and editing methods demonstrate that existing approaches fail to strike a balance between long-term retention and generalization quality. Our findings highlight the need for more robust memory mechanisms that can effectively acquire, update, and preserve knowledge over time in future LLMs. Code will be released upon acceptance.

Ruxi Gu, Zhenliang Zhang, Wei Wang

Department of Automation, University of Science and Technology of China, Hefei, China · State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China.

Knowledge Editing Continual Learning for LLMs LLM Evaluation Persistent Memory for Language Models LLM Memory Catastrophic Forgetting

Jul 29, 2026cs.CL

Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification

Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse first level right, yet once asked for a complete EC number their accuracy at levels two through four drops to almost zero, while specialized models and tools stay usable. We propose EC-Reason-Bench, a training-free, diagnostic evaluation protocol built to answer two questions: why general LLMs score close to nothing on EC number prediction, and how much of that loss can be recovered without updating a single weight. We break enzyme classification ability into four orthogonal levers that can each be measured on their own: output structure, external knowledge, reasoning structure, and reasoning robustness. We test each lever with an inference-time method against a shared zero-shot baseline reproducing previously reported near-zero performance. Experiments with several strong reasoning LLMs yield four main findings. First, external knowledge is decisive and must precede reasoning: uniformly low closed-book performance rises sharply with open-book access, narrowing model gaps. Second, in closed-book settings, whether cascading and chain-of-thought help or hurt depends on a model's tendency to abstain. Third, once evidence is available the aggregate score of the best LLM setting is indistinguishable from simply voting the EC numbers of the nearest retrieved neighbors; that tie is an artifact of averaging, and it hides a large gain on adversarial evidence set against an equally large loss on multi-functional enzymes. Reasoning over evidence therefore acts as an arbiter of conflicting neighbors rather than as a source of knowledge, and no single-number leaderboard can see it. Fourth, accuracy obeys a law of homology availability.

Linyu Li, Zhi Jin, Yichi Zhang +6

School of Computer Science, Peking University, Beijing, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China · School of Computer Science, Tibet University, Lhasa, China

Retrieval-Augmented Generation LLM Evaluation Classification Molecular Property Prediction LLM Reasoning

Jul 28, 2026cs.CL

When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses

Large language models (LLMs) are increasingly used as synthetic users, stand-ins for human respondents whose simulated answers feed product, policy, and market decisions. We ask when this substitution is valid and when it fails, and package the answer as an evaluation framework for intelligent synthetic-user systems. A single protocol, run across four models spanning two families and an 8B-to-frontier capability range, is applied to two independent domains of real human-response data: U.S. general social attitudes (General Social Survey) and cross-cultural values (World Values Survey). Every model is benchmarked against a suite of non-LLM baselines fit on held-out human data. Under demographic prompting and the survey-simulation protocols we test, two failures replicate across both domains, all four models, and both families. First, at the individual level no LLM beats even the strongest baseline; on cross-cultural values every model falls well below it, and the gap survives distance-aware and proper scoring. Second, models systematically over-determine demographics, treating identity as far more predictive of attitudes than it is among real people, a distortion present for nearly every question-group combination and robust to a coding-invariant measure. Neither failure is remedied by a larger, more capable model. A decision-impact analysis shows why this matters in practice: on a segment-targeting task the models inflate between-segment gaps two to fourfold, would direct a team to the wrong segment in half of U.S. and most cross-cultural cases, and manufacture segment splits that do not exist in real people. We publicly release the cross-domain benchmark and validation framework, including all code and data, so that teams can determine in advance when synthetic-user evidence is safe for decision support and when it is not.

Zihan Chen, Di Zhu, Lei Nico Zheng

Stevens Institute of Technology Hoboken, NJ, USA · University of Massachusetts Boston Boston, MA, USA

LLM Evaluation Large Language Model-Based Social Simulation Demographic Bias in Language Models Synthetic Data Evaluation

Jul 28, 2026cs.AI

Position: Evaluation Scores Are Perishable Knowledge Claims

Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation. We argue that evaluation scores should be treated as epistemic claims with three properties: formality (human evaluation provides stronger evidence than an automated metric), scope (a benchmark result applies to the tested distribution, not universally), and validity windows (benchmark results expire as contamination accumulates and distributions shift). Several converging research traditions (chain-of-thought analysis, possibilistic logic, and algebraic theory) establish weakest-link aggregation as the conservative endpoint of a parameterized operator family controlled by a single pessimism parameter. Drawing on those traditions, and on concrete lessons from building an evaluation harness for agentic AI, we propose that evaluation results carry explicit metadata (formality tier, scope declaration, and expiration date) to make their epistemic status transparent. We illustrate the cost of mean aggregation on the public HELM leaderboard: across 54 frontier models on ten scenarios, the top-five models ranked by mean score and by weakest-link are completely disjoint.

Sankalp Gilda, Shlok Gilda

DeepThought Solutions · Meta · University of Florida

LLM Evaluation LLM Reliability

Jul 28, 2026cs.CL

AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology II: Project Planning and Proposal Evaluation

We investigate how well large language models (LLMs) can assist scientific project planning and proposal evaluation. One-page project plans were independently generated for eight expert-conceived research projects in physics, astrophysics, and cosmology by human researchers and three contemporary LLMs (ChatGPT, Claude, and DeepSeek; mid-2025 models, used with their default tool access). The resulting 32 proposals were blindly evaluated by four human reviewers and two newer frontier LLMs (Claude Opus 4.8 and ChatGPT Pro 5.5) using a four-aspect evaluation rubric. Reviewers were also asked to identify whether each proposal was written by a human or an AI. Human reviewers rated human- and AI-written proposals similarly overall, whereas both AI reviewers scored AI-written proposals about one point higher (on a five-point scale) than human-written proposals. Human reviewers correctly identified human- and AI-written proposals 72% and 79% of the time, respectively, while both AI reviewers correctly classified all 32 proposals (100%). These results suggest that current LLMs can produce project plans comparable to human-written ones in the eyes of human reviewers, but that AI reviewers show a systematic preference for AI-generated proposals. Our results suggest caution when deploying LLMs widely in proposal preparation and evaluation.

Jia Liu, Veena Krishnaraj, Kateryna Vovk +18

LLM Evaluation AI-Assisted Scientific Research Language Model Bias Evaluation

Jul 28, 2026cs.CL

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context

India is a vast nation of over 1.4 billion people, varied by hundreds of diverse and locally specific traditions and cultures and 22 officially recognized languages. Large language models (LLMs) are now being deployed on a massive scale throughout the mainland as well as in remote villages. However, the common benchmarks - MMLU, BIG-Bench, and TruthfulQA are almost exclusively English- and Western-centric. They do not identify those safety, fairness, and accuracy failures unique to the Indian context. That is the gap Inspect India Evals seeks to fill. It is an open-source framework built on top of UK AISI's Inspect AI platform. It has six benchmarks: Multilingual MMLU across sixteen Indian languages, BharatBBQ (our adaptation of BBQ for Indian social bias), a safety evaluation for Digital Public Infrastructure, a multilingual safety test using harmful prompts in Indian languages, a multi-turn jailbreak resistance test, and an Indian cultural knowledge benchmark scored using LLM-as-judge rubrics. In this study, we tested five open-weight models ranging from 8B to 32B parameters. Sarvam-M 24B and Gemma 2 27B came out on top, both scoring 80% on the composite India Fairness Index, with Sarvam-M even beating larger 32B models on Indian cultural knowledge and DPI safety compliance. All models scored 100% refusal on Multilingual Safety, whereas DPI safety varied from 20% to 100%. The framework is public. It's built to work with the UK AISI registry. Anyone can reproduce or extend this work.

Abhishek Kumar Singh, Shrey Nag, Sachita +2

GTBIT¹ · TIET² · IGDTUW³ +2

LLM Safety Benchmarks Multilingual Language Model Evaluation LLM Evaluation Cross-Cultural Language Model Evaluation Cultural Bias in Language Models LLM Safety Evaluation

Jul 28, 2026stat.AP

Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM Benchmarks

Item Response Theory (IRT) has recently been proposed as a framework for evaluating large language model (LLM) benchmarks by separating a model's latent ability from the properties of individual benchmark items. Existing neural IRT approaches, including PSN-IRT, estimate these quantities using point estimates, limiting uncertainty quantification and downstream statistical inference. We introduce Laplace-PSN-IRT, a post-hoc last-layer Laplace approximation that augments a trained PSN-IRT model with approximate Bayesian posterior inference, recovering calibrated uncertainty over model ability and item difficulty without retraining. The resulting posterior enables credible intervals, probabilistic comparisons between models, and propagation of parameter uncertainty into Fisher-information-based item selection. We show that most pairwise comparisons among 12 models on a standard LLM benchmark leaderboard are not statistically distinguishable despite differing point-estimate ranks. We further show that point-estimate Fisher information can become nearly zero for many benchmark items because it is evaluated at a single reference ability, whereas posterior-expected Fisher information remains substantially more stable across the ability range. Finally, posterior-expected Fisher information more accurately recovers full-benchmark ability rankings from small benchmark subsets in most experimental settings while matching point-estimate performance for the smallest subsets. We validate the calibration of the approximate posterior using held-out predictive coverage and find that modeling item difficulty as random while treating item discrimination as fixed produces well-calibrated uncertainty in this architecture.

Juan Francisco, Mandujano Reyes

Independent Research

LLM Evaluation Language Model Calibration LLM Uncertainty Estimation Item Response Theory

Jul 27, 2026cs.CL

Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation

Human language is driven by unspoken beliefs and belief updates, making these critical to model for successful communication between large language models (LLMs) and their users. In this paper, we evaluate the ability of LLMs to recognize unspoken beliefs made through implicatures and to understand their updates through implicature cancellation: the pragmatic phenomenon whereby an utterance's implied meaning is weakened or negated. We create the first expert-annotated implicature cancellation dataset, ImplicatureX, crowdsourced for human judgements of implicatures and their corresponding cancellations. We find that LLM belief update understanding lags behind that of humans, especially in more naturally-occurring scenarios. Additional control experiments suggest that successes in LLM belief updates may stem in part from a reliance on prior beliefs, and that failures in belief updates may depend on their type and on their form. Overall, our study suggests that current LLMs have not yet reached human-level understanding of unspoken beliefs and belief updates. Code and data are available at https://github.com/cesare-spinoso/ImplicatureX.

Cesare Spinoso-Di Piano, Verna Dankers, Marius Mosbach +1

Mila - Quebec AI Institute & McGill University · Canada CIFAR AI Chair

LLM Evaluation Pragmatic Reasoning in Language Models Belief Updating in LLMs

Jul 27, 2026cs.CL

CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models

LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched interventions, and generalize beyond the models used to define them. We introduce CogArena, a procedurally generated 13-paradigm benchmark built around a multimethod framework for determining when cognitive-task scores warrant dimensional labels across five theory-motivated groupings. Across 55 open-weight models, nearly all paradigm correlations are positive and a common axis explains about half the variance. The within-grouping advantage is small, scoring-sensitive, and uncertain across model families. In a separately frozen, fully crossed study across 12 models from six families, targeted scaffolds show a small matched-grouping advantage, but no scaffold-specific contrast survives multiplicity correction and selectivity does not improve held-out-family prediction. The frozen confirmation criterion fails. A post-hoc alternate-wording replication produces a smaller positive estimate and again fails. Together, these results support a boundary conclusion. Theory-aligned prompting produces a small in-battery diagonal tendency, but the present evidence does not establish stable five-dimensional profiles. CogArena provides a workflow joining behavioral signatures, covariance, matched interventions, and out-of-family prediction before cognitive labels are attached to model scores.

Dengzhe Hou, Lingyu Jiang, Fangzhou Lin +1

1Graduate School of Information Sciences, Tohoku University · 2Unprecedented-scale Data Analytics Center, Tohoku University · 3Texas A&M University +1

LLM Evaluation Cognitive Modeling

Jul 27, 2026cs.SE

Preliminary Guidelines for Using and Evaluating GenAI Tools to Support Systematic Literature Reviews

Context: Generative AI (GenAI) and Large Language Models (LLMs) are increasingly used for academic tasks in software engineering and beyond, including systematic literature reviews (SLRs). However, while capable of summarizing text, there is no guarantee they can meet the rigour, reliability, and transparency that SLRs require. Objectives: To support researchers intending to conduct SLRs using GenAI or those conducting empirical studies evaluating how well GenAI supports SLR tasks. Methods: First, we conducted a rapid review to identify studies that propose guidelines for evaluating and using GenAI and LLMs to support SLRs. Second, we drew on thought experiments, relevant guidance from the literature, and our own experience conducting SLRs and evaluating tools to develop recommendations for how to use and assess GenAI in the context of SLRs. Results: We discuss the problems researchers face when evaluating GenAI for SLRs. We identify and explain process issues to consider when planning, conducting, and reporting both SLRs using GenAI and evaluations of GenAI tools. Finally, we summarize our results as a set of process recommendations, which we name GUEST (GenAI Use and Evaluation in SLR Tasks). Conclusion: We argue that GenAI requires human oversight and is not currently capable of unsupervised systematic studies. However, it offers the prospect of cost-effective assistance for some repetitive tasks and for additional validation of some complex tasks. Our GUEST recommendations should help software engineering researchers both to conduct and report trustworthy SLRs using GenAI and to provide rigorous independent evaluation studies.

Barbara Kitchenham, Sebastián Pizard, Lech Madeyski +3

Keele University, United Kingdom · Universidad de la República, Uruguay · Wrocław University of Science and Technology, Poland +3

LLM Evaluation Human-in-the-Loop Evaluation Generative AI Evaluation

Jul 27, 2026cs.AI

LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports

Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult. In particular, existing benchmarks are typically static and retrospective, and therefore cannot test how information is synthesized by LLMs to predict future events under uncertainty. We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known. LLM-SoccerArena provides (1) a prospective live benchmark protocol, (2) a public open-source platform, and (3) a factorial benchmark design together with tournament-related questions (e.g., which team will win). LLM-SoccerArena automatically records timestamped, schema-validated forecasts of unresolved events, together with prompts, model versions, tool traces, and costs. The factorial design varies along four dimensions: (1) model version (e.g., GPT-5.5, Claude Opus 4.8); (2) information access; (3) prompting strategy, and (4) forecast horizon. We demonstrate LLM-SoccerArena through a large-scale evaluation of the 2026 FIFA World Cup, in which seven LLMs generated forecasts for all 104 matches and 15 tournament-related questions. We provide a detailed analysis of model performance across information access, prompting strategy, and forecast horizon. As a result, LLM-SoccerArena provides new evidence about the forecasting performance of state-of-the-art LLMs. For example, LLMs with web access outperform those without, but only by a small margin (i.e., a 0.023 improvement in Brier score). Overall, LLM-SoccerArena provides a flexible, open-source platform for prospective benchmarking of unresolved events. LLM-SoccerArena will be continuously updated, and can be directly applied to future national and international tournaments and league competitions.

Jonas Schröder, Jonas Schweisthal, Oliver Müller +2

MCML & LMU Munich Munich, Germany · Paderborn University Paderborn, Germany · University of Cologne Cologne, Germany

LLM Evaluation Forecasting Benchmarks Probabilistic Forecasting Sports Outcome Prediction

Jul 27, 2026cs.CL

INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models

Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce \textbf{INS-ActBench}, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q&A pairs from public exams and sample questions released by 16 actuarial associations. It covers three subsets: \textbf{INS-Act-Know} for standardized actuarial knowledge, \textbf{INS-Act-Case} for long-context insurance case reasoning, and \textbf{INS-Act-Practice} for spreadsheet and R-code tasks with verifiable numerical outputs. Experiments on nine representative LLMs and human actuarial experts reveal a clear capability boundary: frontier LLMs perform strongly on standardized knowledge, but remain much weaker in case reasoning, tool-based workflows, and jurisdiction-sensitive practice. INS-ActBench provides a reproducible foundation for developing actuarial LLMs toward reliable professional assistance. The code is available at https://github.com/FDU-INS/INS-ActBench.

Changyu Chen, Chenwei Lin, Xian Xu

Fudan University

Numerical Reasoning in Language Models LLM Evaluation LLM Tool Use Finance

Jul 27, 2026cs.CL

Accuracy Hides How Language Models Fail: Measuring Failure States Under Matched Output Budgets

Language-model benchmarks collapse two distinct measurement questions into a single accuracy score: whether a response reached an evaluable state, and whether its answer was judged correct. We introduce a two-layer evaluation framework that separates scorer-independent execution evidence, including termination, answer exposure, parseability, and completion length, from scorer-dependent correctness. Across 2,550 outputs from five fixed Qwen and DeepSeek configurations on MATH and ARC-Challenge, matched 2,048-token limits produce sharply different execution mixtures: 49 of 450 Qwen MATH outputs terminate without a final answer, compared with 5 of 300 DeepSeek MATH outputs and none of the 750 ARC outputs. Among the same 300 DeepSeek MATH question-model pairs, no missing-final length termination is observed at 8,192 tokens. A coverage-audited targeted verification study further shows that candidate-selection and aggregation policies can substantially alter comparative accuracy estimates. These results demonstrate that accuracy conflates execution case mix with verification policy. Evaluations of test-time methods should therefore report pre-intervention execution states, verification coverage, and scorer provenance alongside accuracy.

Zongyou Yang, Yinghan Hou

Dyson School of Design Engineering Imperial College London London, United Kingdom · Department of Electrical and Electronic Engineering Imperial College London London, United Kingdom

LLM Evaluation LLM Answer Verification Language Model Generation Evaluation LLM Reliability

Jul 27, 2026cs.CL

Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models

Appending a two-word confirmation tag to a decision question -- "Is X the better choice?" versus "X is the better choice, right?" -- changes whether a language model endorses the choice. We measure this tag effect on 20 frozen, ground-truth-free decisions between two defensible options, counterbalanced so a model's own preferences cancel, scored by exact match on clamped yes/no replies -- no LLM judge, no embeddings. Across 45 models the effect spans +32% to -32% -- a 64-point swing on one word -- with 5 models significantly sycophantic and 17 significantly resistant (BH-FDR q=.10). The sign is a clock: within model families the effect crosses from positive to negative as generations advance (GPT +4 to -28; Claude +7 to -32; Qwen and Grok likewise), roughly -6 points per year, a reversal robust to vendor tier; one lineage (DeepSeek) never crosses, and two releases during the study window (Claude Opus 5, Gemini 3.6 Flash) land on the trend out-of-sample. A full-panel ablation localizes the resistance as a double dissociation: a synonym tag reproduces each model's response almost exactly (r=0.89), while planting the same preference without a tag produces resistance in no resistant model (stance effects +6 to +49; r=0.23 with tag effects). The resistance is keyed to the surface construction of a tacked-on agreement bid, not the user's stance -- a pattern-match, not a principle. And the tag's polarity matters more than its presence: swap one word -- "X is the better choice, maybe?" -- and agreement rises above the neutral baseline in 45 of 45 models (+19.6 points), with ten models affirming both mutually exclusive options at 90-100%. Agreement tracks how sure the user sounds, in opposite directions at the two poles. The instrument is one word, one dollar, and judge-free; run per release, it reads the field's anti-sycophancy training directly off model behavior.

Tapan Parikh

Cornell Tech

LLM Evaluation LLM Sycophancy Language Model Bias Evaluation

Jul 27, 2026cs.CL

Understanding Tone-Dependent Inference Cost in Large Language Models

We examine how prompt tone affects both accuracy of the LLM answers and inference cost as reflected in output-token consumption. Experiments were performed to understand the trade-offs between accuracy and inference cost on a 570 Question MMLU dataset for LLM models prompted in seven different tones from sycophantic to threatening. Our results show that the output-token-length variation substantially exceeded accuracy variation across all models. Output-token consumption varied by up to 44.3% across tone conditions. We also analyzed the tradeoff between the accuracy of the answers and the average output token length in the reasoning process. For the ChatGPT models 4o and 5-nano, the rude tone is quite dominant. For the Gemini models 2.5 Flash and 2.5 Flash Lite, the rude and neutral tones are dominant on the Pareto-optimal frontier. We find that prompt tone influences not only answer quality but also the amount of billable inference resources consumed by modern LLMs.

Akhil Kumar, Om Dobariya

Pennsylvania State University University Park, PA, USA

LLM Inference Efficiency LLM Evaluation LLM Prompting

Jul 26, 2026cs.CL

How Context Attribution Handles What the Model Already Knows

Context attribution methods for large language models (LLMs) identify which input context contributes to the model response. Recent works show the initial success in attributing the con- tributive score of the contexts. However, we observe that when the context overlaps with the training data, these methods can- not disentangle in-context from in-weight (IW) contributions, producing unreliable scores. Based on this observation, in this work, we introduce: 1) an evaluation protocol that relies on four new metrics (base-model context attribution score (BCS), cross-model context attribution consistency (CAC), attribution preservation score (APS), source separation pre- cision (SSP)) and 2) a benchmark dataset (WMDP-Cyber++) with ground-truth provenance labels to systematically assess attribution under IW overlap. In our experiments across four well-known context attribution methods, we demonstrate that they provide unfaithful attribution when the knowledge from the context also exists in the weights. Finally, we adapt these methods for source separation (IW vs. in-context learning (ICL)) and show that they cannot do the disentanglement based on the contributive score

Quoc-Huy Trinh, Lin Zhu, Sebastian Szyller

Aalto University

LLM Evaluation LLM Interpretability Data Contamination in Language Models Training Data Attribution

Jul 26, 2026cs.CL

Zing: Social Mind for LLMs

As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context. This report presents Zhijing, an integrated framework for measuring, internalizing, and grounding social intelligence. For measurement, we introduce SoMBench, a psychology-grounded benchmark spanning 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms. It controls question format, narrative perspective, and context length across 284 shared scenarios and 3,481 expert-verified instances. Evaluation of 20 representative LLMs reveals substantial headroom: the best model achieves only 72.08% overall accuracy, and none of the 17 secondary dimensions reaches the 90% near-ceiling band. For internalization, we develop Zing, a diagnosis-driven training recipe combining supervised fine-tuning, on-policy distillation, and rubric-based reinforcement learning. Across five social-cognition benchmarks, Zing consistently outperforms its base models, with Zing-27B-Stage2 achieving the best average score and Zing-32B-Stage2 remaining competitive with DeepSeek-V4-Pro. For deployment-time grounding, we build Actio, a harness-controlled inference architecture that routes four typed supports into reasoning: PRISM for procedural guidance, Starling for runtime mental-state representation, SAGE for reusable experience, and gated RAG for external social and normative knowledge. Across five base models and three benchmarks, the full harness improves 14 of 15 model-benchmark pairs and is best or tied for best in 8, demonstrating the effectiveness of typed runtime support. Together, these results show that socially intelligent LLMs require coordinated advances in evaluation, parametric internalization, and deployment-time grounding.

Zing Team, Ao Xiang, Bi Jingping +56

LLM Evaluation LLM Grounding Theory of Mind

Jul 26, 2026cs.CL

Do Diagrams Help Large Language Models Reason? Evidence from Syllogistic Reasoning

Diagrams are widely used to support logical reasoning, and prior studies suggest that representations such as Euler diagrams can improve human reasoning performance. Recent work has also explored their effects on large language models (LLMs). In this paper, we compare four representational conditions for syllogistic reasoning: natural language, logical notation, linear diagrams, and Euler diagrams. Using 285 problems from Ando et al. (2024), we evaluate two contemporary LLMs, Claude 3.5~Sonnet and GPT-4o-mini. Our results show that diagrammatic representations do not consistently improve performance. Although the models perform well on entailment and contradiction problems, they struggle with neutral problems and often make systematic conversion errors. Overall, the results suggest that the tested models gain limited benefit from diagrams in logical reasoning tasks.

Risako Ando, Koji Mineshima

Keio University, 2-15-45 Mita, Minato-ku, Tokyo 108-8345, Japan

LLM Evaluation LLM Reasoning

Jul 26, 2026cs.CL

Do LLM Debates Repeat Arguments Differently Across Languages?

LLM debate is usually evaluated by final answers, yet transcripts reveal whether later turns develop new arguments or return to earlier claims in new wording. We study this process with \textit{prior-argument similarity}, which compares extracted argument units with earlier units in the same debate. In controlled eight-turn debates over 71 motions, six languages, and four model agents, Chinese is the only tested language with a consistently positive gap relative to English across three multilingual embedding models. The gap persists across agents, turn positions, regression adjustment, metric variants, extraction-length controls, a second-extractor subset, and cross-encoder tail rescoring. Manual calibration shows weak item-level alignment but a high-similarity tail enriched for substantive repetition. A diversity-aware prompt lowers \textit{prior-argument similarity} across languages, yet does not significantly narrow the Chinese--English gap. Multilingual debate evaluation should therefore measure argumentative development over time and report both average and gap terms.

Huiqian Lai

Syracuse University

Multilingual Language Model Evaluation LLM Evaluation Multi-Agent Debate

Jul 26, 2026cs.CL

Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?

In this paper, we push the boundary of LLM reasoning by testing them in a Chinese language game, xiehouyu, with novel xiehouyu created by linguists that had not existed before to avoid data contamination. We use multiple-choice questions (MCQ), free-form explanation generation, and new xiehouyu creation to evaluate LLMs' ability to understand and create xiehouyu. In MCQ, we use the delta of accuracy (

Δ_{acc}

) between existing but low-frequency xiehouyu and novel ones as an index for memorization.

Δ_{acc}

for native speakers is very low, suggesting similar processing mechanisms. However, we found that frontier Chinese models have on average a

Δ_{acc}

of 23.6%, while English-centric models tested have a mean

Δ_{acc}

of 5.1%, suggesting that frontier Chinese models are likely trained with much larger Chinese data, thus memorizing more low-frequency xiehouyu. For novel xiehouyu, Gemini 3.1 Pro demonstrated remarkable ability with acc 92.6, which is 24% higher than human accuracy. In xiehouyu creation, those created by LLMs receive much worse ratings than those by humans. These results suggest that claims about the reasoning abilities of LLMs may need careful re-examination considering the data contamination issue, and that LLMs' creativity in language-related tasks may still be behind human experts, at least in Chinese xiehouyu.

Hai Hu, Siyuan Song, Chongtian Shao +3

1The Hong Kong Polytechnic University · 2The University of Texas at Austin · 3Shanghai Jiao Tong University

LLM Evaluation Memorization in Language Models Text Generation LLM Reasoning

Jul 26, 2026cs.SE

TLA+-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA Specification Generation

Large language models increasingly write TLA

^{+}

formal specifications from natural-language descriptions, but progress is hard to measure: existing resources grade by resemblance to a reference or by whether the output parses, neither of which shows correctness. We present TLA

^{+}

-Bench, a dataset and benchmark that grades by execution. Every gold specification ships a configuration the TLA

^{+}

model checker runs over the full reachable state space, deciding exactly whether the specification holds the properties that configuration names. The dataset holds 403 model-checked gold and 897 parse-only silver specifications from 13 public repositories, subsumes prior TLA

^{+}

generation data, and carries four model-written descriptions in two styles from two providers, with difficulty and category labels. Our main finding is about measurement itself: an exact oracle gives not one correctness number but a range. Varying only the grading choices earlier benchmarks leave unstated, on one fixed set of model outputs, the correct rate moves sixfold, from 10.0% to 1.7%; adding the interface-supply choice, where the model is told the configuration's names, widens the range to elevenfold, from 18.7% to 1.7%. We call this range the correctness envelope and measure each of its bounds. The findings inside it are stable. Every model writes valid TLA

^{+}

far more often than correct TLA

^{+}

: the strongest is correct 16% of the time by default and 26% when given the interface names, open models at most 1%, and correctness falls sharply with difficulty.

Arslan Bisharat, Eric Spencer, Brian Ortiz +8

Loyola University Chicago Chicago, Illinois, USA

LLM Evaluation Formal Verification Autoformalization

Jul 25, 2026cs.CL

BERT-based Models vs. Large Language Models for Low-Resource Named Entity Recognition: A Comparative Study on Marathi

Named Entity Recognition (NER) for low-resource languages such as Marathi remains a challenging task due to limited annotated resources and linguistic complexity. Although recent Large Language Models (LLMs) have demonstrated strong performance across a wide range of natural language processing tasks, their effectiveness for language-specific NER in low-resource settings remains uncertain. In this study, we fine-tune MahaBERT-v2 on different variants of the MahaNER dataset and systematically compare the performance of these models with an existing MahaNER baseline and prominent general-purpose LLMs, including Gemini, LLaMA-3.3-70B, and Gemma models. All models are evaluated on a Marathi NER test dataset using standard metrics of precision, recall, and F1-score. The experimental results show that the fine-tuned MahaBERT-based models consistently outperform both the baseline and all evaluated LLMs, with the fine-tuned models achieving F1-scores ranging from 0.88 to 0.91, surpassing the existing MahaNER model (0.8843) and significantly exceeding the performance of LLM-based approaches, whose F1-scores range from 0.57 to 0.69. These findings demonstrate that task-specific, language-focused models trained on domain-relevant data remain more effective than general-purpose LLMs for Marathi NER, highlighting the continued importance of specialized architectures for low-resource language processing.

Hariom Ingle, Ronit Ghode, Ishwari Gondkar +2

Department of Information Technology, PICT, Pune, India · L3Cube Labs, Pune, India · Indian Institute of Technology Madras, Chennai, India

Named Entity Recognition LLM Evaluation Transformer LLM Fine-Tuning Low-Resource Language Processing

Jul 25, 2026cs.AI

ESF-Bench: Benchmarking Challenging Slot-Filling Scenarios for Real-World Enterprise Applications

The rapid rise of large language models (LLMs) has driven transformative adoption across enterprises. However, deploying these models in real-world settings presents unique challenges due to complex system constraints and unexpected user behaviors. Among these applications, slot filling is essential for converting unstructured input into structured, actionable data. In this work, we introduce ESF-Bench, a challenging Enterprise Slot Filling benchmark consisting of 810 multi-turn samples and 6530 slots over 8 unique domains. Curated using a taxonomy of the 57 most challenging slot-filling scenarios observed during real-world enterprise deployments, ESF-Bench exposes notable limitations in current state-of-the-art LLMs, with GPT-OSS-120b low successfully extracting slots for only 20.7% of benchmark samples. To support continued research in this area, we publicly release the benchmark dataset, taxonomy, and accompanying evaluation code on GitHub.

Toby Liang, Gopal Sarda, Sagar Davasam +1

ServiceNow

Jul 25, 2026cs.LG

Guarantees on Dynamical System Distinguishability for LLM Token Generation

Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS) and comparing prediction residuals of two DSs. Despite the empirical success of this dynamical approach, a theoretical understanding of why it works, how well it scales as a function of the token sequence, and when it transfers across embedding models remains lacking. We address these questions by formalizing the classification task as a binary hypothesis test between two stochastic linear DSs. We show that the total variation distance between the stationary marginal distributions of the two DSs can be arbitrarily small even when the dynamics differ substantially, which provides a fundamental accuracy floor for any classifier that ignores token dynamics. We then show that the misclassification probability of DS-based classification decays exponentially in the sequence length

L

, with the decay governed by a dynamical discriminability quantity

δ^2

that captures the spectral distance between the two DSs. We also characterize cross-embedding generalization by introducing an approximate intertwining condition between embedding models and establishing a lower bound on the transferable discriminability in terms of the intertwining map's smallest singular value. Together, these results explain the empirical performance of DS-based classification and motivate further investigation into using DS theory to analyze AI systems, in contrast to the more common approach of using AI to model dynamical systems.

Mohamed Akrout, Dan Wilson

Department of Electrical Engineering and Computer Science University of Tennessee, Knoxville, TN, USA

LLM Evaluation Classification