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 28, 2026cs.AI

TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself unexamined. We introduce TRACE (Toulmin-based Reasoning Assessment through Constructive Elements), a metric that analyzes Chain-of-Thought (CoT) reasoning processes. Rather than judging outcomes, TRACE inspects how arguments are constructed by integrating Toulmin's argumentation theory with Flavell's metacognitive framework to assess reasoning structure. Experiments on 26.3K QA samples across 7 reasoning models show strong correlation with benchmark accuracy (r=0.74). Furthermore, TRACE is effective as a reinforcement learning reward signal, outperforming accuracy-only baselines. Together, these results indicate that logically sound reasoning leads to higher-quality answers. TRACE thus serves as a complementary metric for evaluating open-ended outputs. Code is available at https://github.com/hyyangkisti/trace.

Yundong Kim, Heyoung Yang

Applied Agent Research Center, Korea Institute of Science and Technology Information (KISTI), Republic of Korea · Department of Computer Science and Engineering, University of Seoul, Republic of Korea.

LLM Evaluation Language Model Generation Evaluation CoT Evaluation Structured Reasoning LLM Reasoning Reasoning Trace Analysis

May 28, 2026cs.AI

FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification

We introduce FinVerBench, a benchmark and validity study for financial statement verification: determining whether a set of corporate financial statements is numerically consistent from the information shown to the model. FinVerBench is built from SEC 10-K XBRL filings for 43 S&P 500 companies and defines a four-category error taxonomy covering arithmetic, cross-statement linkage, year-over-year, and magnitude perturbations. We attempt fifteen contemporary LLM evaluations and report fourteen complete runs; a Gemini 2.5 Pro run is excluded from the main comparison because 40/108 gateway calls failed. All binary metrics exclude underdetermined positive instances whose perturbed line item is not rendered, leaving a 105-instance observable diagnostic subset (43 clean, 62 error-injected). Under the original guided-checklist prompt on the unrounded diagnostic subset, nine of fourteen complete LLM runs produce 95-100% false positives on clean statements, while one run achieves 0% observed false positives. Benchmark rendering choices materially affect measured recall: on a realistic rounded variant of the same observable subset, the calibrated model's recall is 79.0% with 0% observed FPR, compared with 100.0% recall on the unrounded diagnostic variant. These results support a construct-validity conclusion rather than a final leaderboard: financial statement verification is not merely arithmetic detection, but calibrated judgment under incomplete observability, prompt-induced assumptions, and realistic numerical rendering. FinVerBench and all code are publicly available.

Silu Panda

LLM Evaluation Language Model Calibration Benchmark Validity Finance

May 28, 2026cs.CL

From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals

As candidate generation and high-throughput experimentation advance, the primary bottleneck in materials discovery is shifting from property prediction to making reliable evaluations among massive candidate sets. We propose a Knowledge-Augmented Preference Signals Framework, MaterEval, that automatically produces, for the same candidate, two evaluations: an informed judgment that follows expert rules and provides supporting evidence, and a rule-removed blind guess. By pairing the two evaluations as preference data, we guide general-purpose large language models (LLMs), originally lacking materials-specific criteria, from intuitive judgment toward reliable evaluation supported by explicit evidence. To balance throughput, cost, and reliability, we further introduce a fast-slow reasoning scheme that decouples large-scale rapid screening from in-depth review on a small subset. Using high-entropy alloy (HEA) assessment as a case study, we show that, without external retrieval and relying solely on internalized capabilities, small open-source LLMs achieve substantial gains in accuracy, conclusion consistency, and evidence discrimination, approaching the performance of rule-based closed-source LLMs. These results demonstrate that expert rules can be systematically transformed into learnable preference signals, enabling a low-cost and deployable evaluation module for autonomous materials discovery loops.

Yeyong Yu, Wenya Hu, Xing Wu +1

School of Computer Engineering & Science, Shanghai University, Shanghai, 200444, China. · Center of Materials Informatics and Data Science, Materials Genome2026 Institute, Shanghai University, Shanghai, 200444, China. · Key Laboratory of Silicate Cultural Relics Conservation (Shanghai University), Ministry of Education, China. +1

LLM Evaluation Pairwise Preference Evaluation Materials Science Large Language Model-Guided Scientific Discovery Preference Learning

May 28, 2026cs.AI

When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs

Persona prompting is widely used to steer large language models, yet its practical value remains unclear. Prior work often evaluates persona prompting using aggregate scores, making it difficult to determine whether expert-role prompting consistently improves response quality or instead changes responses along different quality dimensions. We study this question through a controlled comparison of four prompting conditions across 1,140 open-ended questions spanning 38 expert roles and six domains: no role prompt, a generic domain-expert prompt, embedding-based role retrieval, and a hybrid retrieval method combining embedding search with LLM-based role selection. Aggregate results show only small overall differences between conditions. However, metric-level analysis reveals a consistent tradeoff that aggregate averages obscure: role prompting systematically increases expertise depth while reducing clarity. These effects are highly conditional rather than universal. Role prompting performs best on advisory questions and in domains such as medicine and psychology, where structured expert framing and risk communication are intrinsically valuable. In contrast, baseline prompting performs better on conceptual and explanatory questions in finance, legal, science, and technology domains, where concise plain-language explanation is more important. We further show that hybrid retrieval significantly improves over embedding-only role selection, although better role retrieval does not eliminate the broader expertise-depth versus clarity tradeoff. Overall, our findings suggest that persona prompting primarily reshapes response characteristics rather than broadly improving capability, and that multi-metric evaluation is necessary for understanding its effects.

Shuai Xiao, Su Liu, Weikai Zhou +4

Independent Researchers

LLM Evaluation LLM Prompting Persona Prompting Prompt Engineering

May 27, 2026cs.CL

Slogans or Stance? A Label-Light Diagnostic for Entrepreneurial-Discourse Measurement on Chinese SOE Speeches

Dictionary methods, topic models, and embedding-similarity scorers are widely used in CSS and management research to measure constructs such as "entrepreneurial spirit" in corporate speeches. We contribute a label-light measurement diagnostic for such instruments rather than a new extraction model. On a corpus of 80 speeches by leaders of centrally administered Chinese state-owned enterprises, we exploit a natural experiment of 24 same-company different-speaker pairs and 5 same-company same-speaker pairs to test whether a method's per-document indices vary with leader identity holding firm constant. LDA fails (Cohen d=0.20, 95% CI [-0.72, 1.20]); a dictionary scorer reaches d=0.81 and a Chinese sentence encoder d=0.65 on doc-vector distances of order 10^-3. A zero-shot 9B open-weight LLM (Qwen3.5:9b) raises paired-contrast d to 1.09 (exact permutation p1=0.034). We downgrade three claims accordingly: gold F1 measures consistency with the LLM's own prompt rule rather than external construct recovery; doc-level style residualisation cuts the LLM's d to 0.43 (p1=0.22), so roughly half of the effect is consistent with leader idiolect; and a confidence-weighted calibration trades Delta for variance with an auto-mined slogan lexicon near-inert in ablation. We release the 2,190-segment scored corpus, the 170-paragraph pilot, the slogan lexicon, two-family LLM scores, and the evaluation harness.

Ting Gong, Shangquan Sun

Tsinghua University

May 27, 2026cs.CL

UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning

Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We introduce UA-Legal-Bench, a five-task benchmark for evaluating large language models on Ukrainian legal reasoning, built from the Unified State Register of Court Decisions (EDRSR) -- one of the world's largest open judicial corpora (99.5 million decisions). The benchmark comprises: (1) case-type classification (4 classes, n=2,000), (2) judgment form classification (4 classes, n=2,000), (3) case-outcome prediction (6 classes, n=800), (4) legal norm extraction (n=1,794), and (5) cause category prediction (22 classes, n=1,871). We evaluate 11 LLMs (3B--675B) from five families under zero-shot and 3-shot prompting via AWS Bedrock with 158K API calls. Our results reveal sharply task-dependent few-shot effects: few-shot prompting improves judgment form classification by up to +38.6 pp but has mixed effects on outcome prediction. We show that accuracy is misleading on imbalanced legal tasks: the model with highest COP accuracy (62%) is a majority-class predictor (macro-F1: 23%), while the genuinely best model scores only 44% macro-F1. Within-family scaling analysis reveals that 8B models can match frontier performance on surface-level tasks but scaling thresholds vary dramatically across families. We release all data, prompts, and model predictions.

Volodymyr Ovcharov

SecondLayer

Multilingual Language Model Evaluation Legal NLP LLM Evaluation LLM Prompting Legal Reasoning

May 27, 2026cs.SE

SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers

Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studies use narrow datasets, inconsistent metrics, and limited semantic consistency checks. This gap is increasingly important as large language models (LLMs) begin to generate source-like Solidity that may compile and appear plausible, even when its semantics diverge from the original contract. We introduce SCDBench, a dataset and benchmark methodology for LLM-based smart contract decompilation. The dataset contains 600 real-world Solidity contracts with paired bytecode inputs, ground-truth source code, and replayable semantic checkpoints. SCDBench evaluates decompiler outputs through four cumulative stages: format completeness, compilability, Application Binary Interface (ABI) recovery, and semantic consistency via differential replay. We evaluate Claude Opus 4.7, GPT-5.3-Codex, and GLM-5 in a zero-shot decompilation setting, including GLM-5 variants with and without extended reasoning and a zero-shot compilation-repair setting. The results show that frontier LLMs can often produce structured and compilable Solidity, but achieving semantic consistency remains far from solved: the best-performing frontier model perfectly decompiles only 42/600 contracts. We further show that introducing same-model compilation repair substantially improves performance at modest additional cost. SCDBench establishes a common ground for rigorous, reproducible evaluation and aims to accelerate the development of reliable smart contract decompilers for blockchain security and transparency.

Kaihua Qin, Dawn Song, Arthur Gervais

University of Warwick · UC Berkeley · University College London

LLM Evaluation Differential Testing

May 27, 2026cs.LG

The Routing Plateau: Understanding the Accuracy Limits of LLM Routers

LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by adaptively selecting a model for each query. Recent work has explored a broad range of routing methods, including clustering-based routers, learned classifiers, pairwise ranking, and confidence-based approaches. Our extensive study of 21 routing methods across five benchmarks reveals a consistent phenomenon that we call the routing plateau (Fig. 1): many methods, including kNN, achieve very similar accuracy and converge to a narrow performance range that remains far below the oracle router. Our analysis supports a correctness-prediction bottleneck hypothesis: current routers primarily learn global-average model performance trends rather than fine-grained, query-specific routing signals. As a result, they collectively fail on queries that require instance-specific routing decisions. Moreover, to understand whether the plateau can be alleviated with a better training setup, we construct a 300K-query benchmark (Nine-by-300k). More data, larger encoders, and end-to-end fine-tuning improve eight routers by 1.24 pp on average, but leave the plateau largely intact. These findings suggest that further progress may require inputs beyond the query itself, such as partial output trajectories that reveal how models attempt the task.

Yifan Lu, Qiyue Zhang, Shenrun Zhang +4

Rice University · Amazon

LLM Evaluation Adaptive Model Routing LLM Routing

May 27, 2026cs.AI

Mind Your Tone: Does Tone Alter LLM Performance?

The use of Large Language Models (LLMs) is proliferating, yet their performance is observed to vary based on prompting styles and tones. In this study, we investigate both whether and how tonal variations in prompts lead to disparate LLM accuracy for objective multiple-choice questions. We use two datasets: a 50-base question dataset with five tone variants and a 570-base question MMLU subset spanning 57 subjects with seven tone variants. Experiments were conducted to evaluate the performance of four cost-efficient, popular LLMs: ChatGPT-4o, ChatGPT-5-nano, Gemini 2.5 Flash, and Gemini 2.5 Flash Lite. Across models, tonal effects are systematic but highly model-dependent. Some models show small, yet statistically significant, shifts, while others exhibit large accuracy swings across tones. Further, we identify subject-level differences in tone sensitivity and present a routing framework to explain how tones may attune internal reasoning modes. Our findings caution users against assuming tone-robust reliability in LLM deployments.

Om Dobariya, Akhil Kumar

Pennsylvania State University University Park, PA, USA

LLM Evaluation LLM Prompting Language Model Robustness

May 27, 2026cs.AI

When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis

Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes what policymakers see and which arguments register. Standard evaluation, anchored on stance accuracy against a small validated set, cannot detect when different models produce materially different categorizations of the same public input. We propose an Interpretive Audit Pipeline that treats multi-model disagreement as diagnostic of interpretive complexity and directs human review toward genuinely ambiguous public input. Analyzing 1,260 public comments on a federal USDA docket across four LLMs, we find that inter-model thematic divergence exceeds within-model prompt variation, and that an expert rubric suppresses deep interpretive disagreement without resolving it. In a two-stage labeling study on a stratified 40-comment subsample, four LLMs and a human annotator labeled independently and then revised after seeing the others' labels. Revision behavior varied across labelers, and the human annotator's revisions frequently introduced framings absent from the ensemble's collective output. We argue disagreement-based evaluation is a necessary complement to accuracy metrics for LLM-assisted interpretive coding.

Aisha Najera, Alvin Moon, Vedant Srinivasan +1

AI Lab, Princeton University · Engineering and Applied Sciences, RAND Corporation · Science, Technology, and International Affairs, Georgetown University

LLM Evaluation Annotator Disagreement LLM Auditing LLM-Assisted Annotation

May 27, 2026cs.CL

The Trust Paradox: How CS Researchers Engage LLM Leaderboards

Large language model (LLM) leaderboards rank AI models using standardized benchmarks and have become highly visible across computer science, despite known limitations in their reliability and robustness. Yet how they shape researchers' actual practice remains empirically uncharted. We address this gap through semi-structured interviews with eight researchers across four computer science subfields, analyzed using reflexive thematic analysis. We find a near-universal paradox of pragmatic skepticism: while participants expressed deep distrust of leaderboard rankings, they continued to use them as rough decision-making aids. Peer networks, not leaderboards, emerged as the primary model selection mechanism, and arena-based (human-voting) leaderboards were consistently preferred over static benchmark leaderboards. Leaderboard influence varied sharply across subfields, revealing that disciplinary culture, not individual attitudes, mediates engagement; for instance, NLP researchers faced state-of-the-art comparison pressure while HCI and Systems/Privacy researchers reported none. Across these differences, however, participants converged on cost transparency as the most demanded missing feature (seven of eight). We translate these findings into concrete design recommendations that align evaluation infrastructure with how researchers actually use it, such as task-specific score breakdowns, cost integration, and voter-demographic disclosure.

Pouya Sadeghi, Anamaria Crisan, Jimmy Lin

University of Waterloo Waterloo, Canada

Model Selection LLM Evaluation Benchmark Validity

May 27, 2026cs.LG

PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective

Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking the retention of pretrained capabilities. We argue that PEFT should be assessed through the stability-plasticity dilemma: the trade-off between target-task adaptation and resistance to forgetting. We introduce PEFT-Arena, a benchmark that jointly measures downstream performance and general capability retention. Across methods, we find distinct stability-plasticity profiles; under comparable parameter budgets, orthogonal finetuning achieves the most favorable Pareto frontier. To explain these differences, we analyze PEFT updates from two geometric perspectives. In weight space, spectral analysis reveals how parameterizations interact with the pretrained singular-value structure. In activation space, retention metrics show whether finetuning preserves or distorts general-capability representations, with forgetting linked to non-isometric representation distortion. Finally, an analysis shows that final SFT checkpoints often overshoot a better target-retention operating point. Inspired by this, we present case studies of a post-hoc improvement with path-wise rewinding.

Yangyi Huang, Ruotian Peng, Zeju Qiu +4

The Chinese University of Hong Kong · Westlake University · MPI for Intelligent Systems

LLM Evaluation Fine-Tuning Parameter-Efficient Fine-Tuning Catastrophic Forgetting

May 27, 2026cs.CL

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is synthesized, propagated, or corrupted over time. In this work, we study the new problem of error tracing and attribution in LLM memory systems. We propose a novel framework that transforms memory pipelines into executable memory evolution graphs, enabling fine-grained tracing of operational information flow. We then construct MemTraceBench, a benchmark collected from representative memory systems such as Long-Context, RAG, Mem0, and EverMemOS, to systematically study memory failure modes. We further introduce an automatic attribution method that iteratively traces operation subgraphs to pinpoint the root cause of any failed case. Our analysis reveals that memory failures are systematic, stemming from operation-level issues like information loss and retrieval misalignment. Crucially, we leverage these fine-grained attribution signals to guide downstream prompt optimization, establishing a closed-loop system that automatically corrects faults and boosts end-task performance by up to 7.62 percentage points. Code has ben released at https://github.com/zjunlp/MemTrace.

Xinle Deng, Ruobin Zhong, Hujin Peng +15

Zhejiang University · Alibaba Group

LLM Evaluation Memory-Augmented Language Models LLM Memory

May 27, 2026cs.AI

The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic

The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-generated variants of GSM8K problems, concluding that the models lack genuine reasoning capabilities. We argue that this conclusion rests on shaky statistical ground. Re-evaluating 20 open-weight models using bootstrapped Generalised Linear Mixed Models with per-question random effects, we find that only 8 exhibit statistically significant performance changes under the original prompt format. Moreover, we identify a previously unacknowledged factor: the distribution of integers in problem texts of the main GSM-Symbolic dataset is systematically shifted towards larger values relative to the original GSM8K (K-S statistic = 0.12, p < 0.001), contradicting the original authors' claims. Controlling for this large-number effect accounts for significance in half of the remaining cases. Among models with statistically significant performance deltas, we identify distinct, model-specific behavioural failure profiles -- including fragility of variable binding, arithmetic limitations, and dual-task interference -- underscoring that blanket claims about LLM reasoning risk being both statistically premature and mechanistically misleading.

Dominika Agnieszka Długosz, Arlindo Oliveira, Natalia Díaz-Rodríguez

Instituto Superior Técnico & INESC-ID, Universidade de Lisboa, Portugal · Dept. of Computer Science and AI & DaSCI Institute, Universidad de Granada, Spain

LLM Evaluation Generalized Linear Models LLM Reasoning

May 27, 2026cs.CL

Measuring Form and Function in Language Models

We introduce quantitative metrics for child language acquisition to evaluate language models. Our focus is on the formal syntactic and functional discourse properties of determiners in English, which young children acquire early and accurately. We propose Contextual Alternative Choice (CAC), a new prompting method which provides targeted tests for both syntactic and discourse knowledge of language. The method enables direct comparison of language models against children, and more importantly, against statistical benchmarks independently established in empirical research. No current model trained on a comparable amount of data simultaneously meet both formal and functional benchmarks like human children, but some very large models do. We present our results as methodological and technical contributions, with specific emphasis on cognitive status of language models.

Héctor Javier Vázquez Martínez, Charles Yang

University of Pennsylvania Department of Linguistics and Computer and Information Science

LLM Evaluation Child Language Acquisition

May 27, 2026cs.AI

Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability

Large language models (LLMs) are increasingly used for tasks that implicitly reduce to Boolean satisfiability (SAT), yet their reasoning ability on SAT remains unclear. We present a systematic study of LLMs on 2-SAT and 3-SAT, together with two canonical reductions, Vertex Cover and discrete 3D packing, to probe representation-invariant reasoning. We first evaluate models using conventional metrics, including accuracy, precision, recall, and F1, as well as the SAT phase-transition setting. We find that these metrics can be misleading: many models obtain high scores by over-predicting satisfiable formulas, fail to reproduce the classical easy-hard-easy signature around the 3-SAT threshold, and degrade sharply as the number of variables grows. To address this problem, we introduce a paired-formula protocol based on minimally different satisfiable and unsatisfiable instances, together with Accurate Differentiation Rate (ADR), which requires both members of each pair to be classified correctly. ADR separates reasoning-oriented models from heuristic ones and correlates with witness validity. Beyond CNF, we test cross-representation consistency by converting CNF to Vertex Cover and 3-SAT to discrete 3D packing. Model decisions on CNF and on the corresponding graph or packing instances agree for most models on more than 80 percent of instances, suggesting stable decision rules across representations. Overall, our results show that SAT is a conservative probe for LLM reasoning, and that paired evaluation with ADR provides a more faithful and representation-robust assessment than conventional metrics.

Leizhen Zhang, Shuhan Chen, Sheng Chen

University of Louisiana at Lafayette, Lafayette, USA · East China Normal University, Shanghai, China

LLM Evaluation Constraint Satisfaction LLM Reasoning

May 27, 2026cs.AI

MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation

Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Existing benchmarks focus primarily on generating single-part CAD models and evaluate them using geometric similarity metrics that fail to capture functionality, manufacturability, and assemblability. To address this gap, we introduce MUSE, a Text-to-CAD benchmark focused on complex, editable boundary representation (B-Rep) assemblies. MUSE pairs practical design instances with structured Design Specifications and evaluates generated models through a three-stage protocol: code check, geometric check, and design-intent alignment. The final stage uses design-specific rubrics to assess functionality, manufacturability, and assemblability, moving beyond shape matching toward practical design quality. To enable scalable evaluation, we use a rubric-based visual language model (VLM) judge and validate its reliability through human annotation. Experiments on closed-source and open-source LLMs reveal a clear failure cascade from executable code to valid geometry and finally to engineering-ready design, with even the strongest models achieving limited success on fine-grained engineering criteria. Together, MUSE provides a realistic benchmark and evaluation framework for advancing Text-to-CAD from geometric generation toward true engineering design. Our project website, including the leaderboard, dataset, and code, is available at https://dong7313.github.io/muse-benchmark/.

Xiaoyu Dong, Zhi Li, Xiao-Ming Wu

1The Hong Kong Polytechnic University · 2Curvature Flow Co., Limited

LLM Evaluation Text-to-CAD Generation

May 27, 2026cs.AI

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However, existing methods for adaptive thinking-mode selection are typically evaluated under different models, datasets, and implementation assumptions, making it difficult to compare their practical behavior. We introduce HRBench, a unified evaluation framework for studying thinking-mode switching in hybrid-reasoning LLMs. HRBench organizes the design space along two axes: three switching strategy families, prompt-based selection, external routing, and speculative execution, and four training regimes, training-free, SFT, offline and online RL, yielding 12 controlled evaluation settings. We evaluate these settings across 6 LLMs, from Qwen3.5-2B to Kimi-K2.5-1.1T, and 5 reasoning benchmarks covering mathematics, science, and code, while reimplementing 12+ representative prior methods within the same pipeline. Our analysis characterizes how different switching strategies occupy distinct effectiveness-efficiency trade-off regions: prompt-based methods often provide favorable token-accuracy trade-offs, routing methods offer more stable cost reduction, and speculative methods tend to improve accuracy at higher token cost. We further find that training affects strategies differently, and that the preferred strategy varies with model scale and task domain. HRBench provides reference implementations and a unified evaluation platform to support more controlled research on efficient reasoning in hybrid-reasoning LLMs. Our data, code and repository are available at https://github.com/usail-hkust/HRBench.

Yansong Ning, Mianpeng Liu, Jingwen Ye +2

AI Thrust, The Hong Kong University of Science and Technology (Guangzhou) · AIPD, Tencent

LLM Evaluation Adaptive Inference LLM Routing Efficient Language Model Inference Large Reasoning Models

May 27, 2026cs.CL

Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach

Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality of arguments requires a rigorous evaluation. We investigate the extent to which LLMs can effectively perform this task. We tested 12 open-weight LLMs of different sizes and families under zero-shot, few-shot, and chain-of-thought to approximate human pairwise comparisons of argument quality across three dimensions--logical, rhetorical, and dialectic--and used these comparisons in a Bradley-Terry model to infer latent strength scores and derive a ranking of arguments. Our insights show that LLMs have promising but moderate correlation with human judgment, with Llama-70B obtaining the strongest alignment, reaching moderate Cohen's

κ

= 0.493 and moderate correlations with Bradley-Terry scores derived from these annotations (Kendall, Pearson, and Spearman: 0.327-0.477). Other LLMs exhibit weak, moderate, or high alignment with Llama-70B while achieving comparable results against human judgment, suggesting partial but complementary understanding of underlying quality dimensions despite differences in model size and family. Moreover, LLM predictions are stable across trial runs, with fewer than 7.75% of cases yielding different labels. Remaining variability is handled via majority voting and few-shot prompting for large-size models.

Nicolás Benjamín Ocampo, Agnes Paullate Nyiranziza, Davide Ceolin

1Centrum Wiskunde & Informatica, The Netherlands · 2Vrije Universiteit Amsterdam, The Netherlands

LLM Evaluation Pairwise Ranking

May 27, 2026cs.CL

BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law

We introduce BenGER (Benchmark for German Law), a benchmark and dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The dataset combines 596 exam-style free-text legal case tasks across multiple levels of legal education and 531 short doctrinal reasoning tasks. It includes a controlled validation subset of timed human-written solutions under both unaided and human-AI co-creation conditions. We evaluate 12 contemporary LLM systems - closed flagship, efficiency-oriented, and open-weight - with a rubric-aligned LLM-as-a-Judge cross-validated against a multi-rater human-grading layer (three blind reviews per solution, six judge families benchmarked against the human pool). Closed-flagship systems lead the leaderboard across all three corpora, human-AI co-creation measurably improves on unaided human work, and the LLM judge tracks human grading at Pearson r=0.76 and Cohen's k=0.60. System rankings are stable across judge families and two judges from independent providers clear the Calderon single-reviewer replacement bar on human-authored solutions.

Sebastian Nagl, Ann-Kristin Mayrhofer, Martin Heidebach +6

Technical University of Munich (TUM) · Ludwig Maximilian University of Munich (LMU) · University of Konstanz +1

Legal NLP LLM Evaluation LLM-as-a-Judge Legal Reasoning

May 27, 2026cs.CL

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. However, prior approaches face generalization limitations from two aspects: focusing on benchmark-level performance introduces scenario-specific artifacts, while relying on IID validation loss fails to track capability improvements when training distributions vary. In this work, we argue that downstream scaling should be studied at the capability level, which captures shared skill factors across related tasks while abstracting away benchmark-specific noise. We propose SuperValid, a framework that synthesizes OOD (out-of-distribution), capability-aligned validation data by distilling core concepts from benchmarks within a capability domain and expanding them into diverse, knowledge-rich texts. Extensive experiments spanning 16 benchmarks grouped into 6 capability domains show that SuperValid loss exhibits strong and stable correlation with downstream performance across models of different architectures, scales, and training data distributions. As a training-free metric computable during training without benchmark evaluation, SuperValid enables effective model selection, early stopping, and scaling decisions.

Quanen Sun, Changxin Tian, Ke Shi +6

Ant Group

LLM Evaluation Language Model Scaling Laws OOD Generalization

May 27, 2026cs.CL

ATLAS: All-round Testing of Long-context Abilities across Scales

Long-context language models now advertise context windows up to millions of tokens, yet evaluations typically report a single length or a narrow task family, masking two failure modes: performance can collapse as length grows, and strong retrieval need not transfer to downstream use. We present ATLAS, a benchmarking framework that redefines long-context evaluation as length-dependent capability profiling. ATLAS contributes three methodological principles:(i) a layered taxonomy separating foundational operations from application workloads so failures can be attributed, (ii) length-aware AUC scoring that integrates score-length curves over a fixed 8K-1M grid, replacing single-point metrics with full degradation profiles, and (iii) ATLAScore, a harmonic-mean aggregate over taxonomy categories that penalizes imbalanced profiles, with end-to-end uncertainty propagation from subset scores through the nonlinear final aggregate. We instantiate the framework across eight capability dimensions with nine auditable components and 6,438 instances, and evaluate 26 models. Gemini-3.1-Pro-Preview leads at 128K, Claude-Opus-4.6 leads at 1M. Rankings reshuffle substantially between ATLASscore@8K-128K and ATLASscore@8K-1M: 7 models move by at least two ranks, and the two taxonomy layers share only 61% of cross-model variance, with individual rank gaps up to 12 positions. These results support reporting long-context quality by capability and length, not by a single headline score.

Deli Huang, Cunguang Wang, Hongyin Tang +15

Meituan · Fudan University

LLM Evaluation Benchmark Construction Long-Context Language Model Evaluation Long-Context Modeling

May 27, 2026cs.AI

PetroBench: A Benchmark for Large Language Models in Petroleum Engineering

Large Language Models are increasingly applied in the petroleum industry, highlighting the need for a domain-specific evaluation framework. This study develops a benchmark for LLMs in petroleum engineering, including a three-stage process of data preprocessing, quality filtering, and multi-model validation. Using expert review, a standardized question bank with strong domain relevance and discriminative capability was constructed. The benchmark covers production, reservoir, and drilling engineering, with 1,200 questions across multiple-choice, true or false, term definition, and short-answer formats. Eight mainstream LLMs were evaluated under a unified API environment. Results show that models performed better on subjective than objective questions, indicating weaknesses in factual knowledge discrimination. The highest accuracies for multiple-choice and true or false questions were 65.3% and 74.3%, respectively. Gemini-3-Pro, Kimi-K2.5, and Claude-Opus-4.6-Thinking achieved the best overall scores of 72%-74%. Models performed best in production engineering and weakest in reservoir engineering. Chinese models showed advantages in multiple-choice questions, while international models performed slightly better in short-answer questions. The benchmark provides a reproducible and practical reference for evaluating and deploying LLMs in petroleum engineering.

Xiang Wang, Tingting Zhang, Sen Wang +4

School of Petroleum and Natural Gas Engineering, Changzhou University, Changzhou 213164, China · China University of Petroleum (East China), Qingdao, Shandong 266580, China

LLM Evaluation Question Answering

May 27, 2026cs.CL

The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates

With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-trained models are optimized for next-token prediction and often fail to follow instructions or produce well-formed answers under standard prompting and direct decoding. As a result, benchmark performance can conflate model capability with decoding-induced failures to produce task-oriented outputs, while exposing such behavior often relies on costly post-training. Recent decodingonly approaches attempt to reshape output distributions, but such methods can be inefficient and brittle across open-ended tasks. To address these limitations, we propose Energy-Based Decoding (EBD), a training-free, reward-guided framework for activating task-oriented behaviors from frozen pre-trained LLMs across both open-ended and objective tasks. EBD augments decoding with an external lightweight reward model, steering generations toward high-utility responses while anchoring them to the pre-trained model prior through a reward-tilted target distribution. We show that EBD shifts base-model outputs toward more instructionfollowing behavior, increasing behavioral similarity to post-trained counterparts and enabling a fairer inference-time evaluation of accessible pre-trained-model behavior. Empirically, EBD outperforms baselines across five models and six benchmarks, improving Qwen3-8B-Base on AlpacaEval2.0 from 8.8 to 44.5, reducing Mistral-7B Math500 latency by 18.9x relative to prior decoding work, and remaining robust to reward-model size.

Shaobo Wang, Guo Chen, Ziyue Wang +5

Shanghai Jiao Tong University · Qwen Team, Alibaba Group · The Chinese University of Hong Kong, Shenzhen

LLM Evaluation Language Model Decoding Instruction Following

May 27, 2026cs.CL

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations

Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper systematically pressure-tests probe-based metrics across the Gemma 3 model family (1B-27B parameters), diagnosing why they fail rather than merely documenting that they fail. We test four hypotheses about deception encoding: (1) single linear direction, (2) multi-dimensional subspace, (3) convex conic hull, (4) entropy proxy. Our design includes cross-domain transfer matrices, multi-dimensional probe analysis with permutation null baselines, entropy-residualization tests, and distractor evaluations across 8 stylistic shifts. We find that: (a) probes achieve near-perfect AUROC (>=0.998) on clean data but collapse under stylistic shifts; style-augmented probes recover near-perfect detection (mean AUROC 0.979-0.983) on unseen styles; (b) the single-direction hypothesis is rejected (k=1 captures only 0.61-0.80 AUROC), with cross-domain transfer failure confirmed as geometric rather than layer-mismatch-driven; (c) the entropy-proxy hypothesis is rejected (max |rho|=0.454, max Delta-AUROC after residualization=0.004); and (d) deception does not form a significant linear subspace (per-domain k*=0), yet multi-dimensional probes (k>=5) recover the signal through distributed sub-threshold features. Probe fragility reflects distributional narrowness rather than an architectural limitation: style-augmented probes recover near-perfect detection at both 4B and 27B, establishing that the inverse scaling pattern is a training-distribution artifact rather than a genuine scale-dependent phenomenon.

Sachin Kumar

LexisNexis, USA

LLM Evaluation Language Model Safety Evaluation LLM Interpretability Deception in Language Models Language Model Robustness Representation Geometry in Language Models+1

May 27, 2026cs.CL

Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm

Benchmarking is mature where answers are verifiable -- math, code, reasoning -- but the fastest-growing uses of LLMs are subjective and human-facing: companionship, emotional support, counseling. There the default validity test, correlating a metric to human judgment, has no stable anchor: inter-rater agreement is low, structured by annotator identity, barely reproducible, and length-biased. So we cannot answer the question that matters: does capability that scales on objective benchmarks transfer to subjective behavior, and would our instruments even tell us if it did not? We build an instrument for this regime and report what it reveals at the frontier. We contribute, first, a self-evolving instrument that selects and then authors its own behavioral dimensions under a multiplicative anti-gaming fitness, self-halting when it stops improving; second, a trust-by-construction paradigm that earns belief through three certificates established without a human gold standard, where human raters saturate (rho ~ 0.45); and third, the finding it makes visible -- capability transfer is dissociable. Across 49 models, 8 families, and 24 months, subjective behaviors are where objective-benchmark scaling fails to carry over: the sharpest case, advice-restraint (knowing when not to give advice), is the frontier's universal-lowest dimension, and at gpt-4.1->gpt-5 it ran backwards while the aggregate score hid it -- a regression one instruction recovers. Warm restraint is moved by model generation, not by raw scale, MoE width, inference budget, or reasoning mode; the open-weight Pareto frontier matches closed flagships at ~10-80x lower per-call cost; and four judge families replicate the rubric on held-out human ESConv conversations. Data, code, the locked rubric, and judge prompts will be released upon publication.

Yuming, Huang, Yao Liu +3

Rapheal · Cylingo team

LLM Evaluation Benchmark Validity Automated Evaluation

May 27, 2026cs.AI

SuiChat-CN: Benchmarking Contextual Suicide Risk Assessment in Chinese Group Chats

Suicide is a critical global public health challenge, causing approximately 720,000 deaths each year and calling for timely, effective prevention strategies. Existing computational studies primarily focus on post-based social media platforms such as Twitter and Weibo, leaving instant messaging environments such as Telegram underexplored. Yet group chats pose distinct challenges: messages are short, fragmented, multi-party, and often rely on implicit or culturally specific expressions, making isolated post-level analysis insufficient. We introduce SuiChat-CN, a Chinese group-chat benchmark for contextual suicide risk assessment. We collect public Telegram group-chat data, construct coherent conversational segments through signal-word extraction and bidirectional context expansion, and annotate user risk levels with an expert-validated, LLM-assisted paradigm. SuiChat-CN contains 13,312 contextual segments from 1,406 users, covering 258,228 raw chat messages. Extensive experiments with PLMs and more than 40 LLMs demonstrate that contextual information is essential for reliable risk assessment, while fine-tuning and partial-context evaluation further reveal the challenges of early detection in multi-party conversations. Due to ethical and sensitivity concerns, the dataset is not publicly released but will be shared with accredited mental health and suicide-prevention research institutions upon reasonable request.

Xiangyu Wang, Zhiwei Yu, Chengze Du +3

University of Chinese Academy of Sciences · 2Tsinghua University · 3Beijing University of Posts and Telecommunications +1

Social Media Analysis LLM Evaluation Suicide Risk Modeling Clinical Risk Prediction

May 27, 2026cs.CL

FinBoardBench: Benchmarking Dynamic Wealth Management and Strategic Financial Reasoning of LLMs via Board Game Simulations

Recently, large language models (LLMs) have achieved superior performance in static financial reasoning and simple dynamic trading tasks. However, existing static financial benchmarks are insufficient to assess the dynamic wealth management and financial decision-making capabilities of LLMs in real-world environments. To bridge this gap, we present FinBoardBench, an evaluation suite based on three classic financial board games: Cashflow, Acquire, and Monopoly. FinBoardBench assesses a comprehensive set of financial skills, including personal cash flow management with debt balancing, corporate investment and acquisition forecasting, and competitive trade negotiations with asset auctions. Our experiments with 9 advanced LLMs reveal that while exhibiting basic long-term planning and investment logic, they fail to effectively leverage complex interactions for profit, and their strong static reasoning performance does not transform into successful dynamic decision-making. Notably, they tend to prioritize immediate asset acquisition over maintaining sufficient liquidity, making them vulnerable to financial crises triggered by random events. We hope that FinBoardBench can provide a valuable reference for more intelligent LLM-based decision-making systems in the future.

Xuesi Hu, Peng Wang, Jinpeng Miao +7

School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China · School of Economics, Anhui University, Anhui, China · SKLPlanets, Macau University of Science and Technology, Macau, China +2

LLM Evaluation Finance Financial Decision-Making

May 27, 2026cs.AI

PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management

Large language models (LLMs) have shown strong performance across diverse financial tasks, yet portfolio management (PM) remains poorly benchmarked. Existing benchmarks exhibit two gaps: they are often equity-only and ignore cross-asset correlations; they fail to evaluate the complete PM decision pipeline. We introduce PortBench, a benchmark spanning six heterogeneous asset classes from 2015 to 2025. PortBench comprises a static QA dataset of 6,269 questions across seven task templates and a dynamic five-stage allocation pipeline. To evaluate these layers, we introduce two metrics: a dual-layer correlation score for inter-class hedging and intra-class concentration, and CEPS, which quantifies how reasoning errors compound across pipeline stages. We further evaluate under three stress windows and three risk profiles, and support real-time evaluation to mitigate pretraining contamination on historical markets. Across ten frontier LLMs, strong financial QA performance fails to translate into superior portfolio performance: only 32.5% of 120 evaluations beat equal weighting on Sharpe across four market periods. Our source code is available at this https URL.

Yuxuan Zhao, Sijia Chen, Ningxin Su

1Yantai Research Institute of Harbin Engineering University · 2The Hong Kong University of Science and Technology (Guangzhou)

LLM Evaluation Quantitative Finance LLM Decision-Making Portfolio Optimization Finance

May 27, 2026cs.CL

ChildEval: When large language models meet children's personalities

While LLMs enable personalized chatbots, their effectiveness in child-centered personalization remains unclear, as systematic evaluation of child-specific preferences is still lacking. To address this gap, we introduce ChildEval, a benchmark for evaluating LLMs' ability to infer and follow child-centered preferences in long-context conversations. ChildEval contains 29K synthesized persona profiles of children aged 3-6, providing relatively static background information. Each persona is associated with a child preference-which may align with, conflict with, or be independent of the persona-expressed either explicitly in a single sentence or implicitly through 6-10 turn dialogues. Explicit and implicit preferences are designed to reflect the same underlying preference but differ in expression, capturing dynamic aspects of preference expression rather than changes in the static persona. The benchmark spans five top-level and fourteen sub-level categories covering children's daily lives and development. We further propose fine-grained, child-centric evaluation protocols to systematically assess open-source LLMs. Experimental results demonstrate how different personalized representations affect LLM responses and suggest that finetuning on ChildEval can enhance child-centered performance. Our code and dataset are available at https://github.com/ziyanluo/ChildEval.

Yanyan Luo, Xue Han, Chunxu Zhao +5

JIUTIAN Research, China Mobile, Beijing, China

LLM Evaluation LLM Personalization Personality Modeling in Language Models Personalized Language Models