LLM Evaluation

LLM: Large Language Model

Follow this topic Ask about this topic

The field studies how to measure language-model capabilities, reliability, and risks, and whether those measurements support sound comparisons and deployment decisions. Approaches include curated and synthetic benchmarks, psychometric and adaptive testing, execution-based checks, robustness tests, and human or LLM-based judges. Researchers also examine calibration, uncertainty, contamination, prompt sensitivity, and whether scores reflect the intended capability across languages and domains. A central tension is that efficient aggregate scores can hide important errors and measurement biases, while more realistic, human-grounded evaluations are costly and difficult to standardize.

Latest papers

2,432 papers286 papers in the last four weeks, up 16% on the four weeks before. 1.7% of all new papers.

Mar 15, 2026

Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains

The minimal pairs paradigm of comparing model probabilities for contrasting completions has proven useful for evaluating linguistic knowledge in language models, yet its application has largely been confined to binary grammaticality judgments over syntactic phenomena. Additionally, standard prompting-based evaluation requires expensive text generation, may elicit post-hoc rationalizations rather than model judgments, and discards information about model uncertainty. We address both limitations by extending surprisal-based evaluation from binary grammaticality contrasts to ordinal-scaled classification and scoring tasks across multiple domains. Rather than asking models to generate answers, we measure the information-theoretic "surprise" (negative log probability) they assign to each position on rating scales (e.g., 1-5 or 1-9), yielding full surprisal curves that reveal both the model's preferred response and its uncertainty via entropy. We explore this framework across four domains: social-ecological-technological systems classification, causal statement identification (binary and scaled), figurative language detection, and deductive qualitative coding. Across these domains, surprisal curves produce interpretable classification signals with clear minima near expected ordinal scale positions, and entropy over the completion tended to distinguish genuinely ambiguous items from easier items.

Andrew Katz

Department of Engineering Education, Virginia Tech

LLM Evaluation Surprisal Theory Confidence Estimation in Language Models

Mar 14, 2026

QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models

While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evaluations rely heavily on multiple-choice questions, failing to capture the unstructured, ambiguous, and long-tail complexities inherent in genuine user inquiries. To bridge this gap, we introduce QuarkMedBench, an ecologically valid benchmark tailored for real-world medical LLM assessment. We compiled a massive dataset spanning Clinical Care, Wellness Health, and Professional Inquiry, comprising 20,821 single-turn queries and 3,853 multi-turn sessions. To objectively evaluate open-ended answers, we propose an automated scoring framework that integrates multi-model consensus with evidence-based retrieval to dynamically generate 220,617 fine-grained scoring rubrics (~9.8 per query). During evaluation, hierarchical weighting and safety constraints structurally quantify medical accuracy, key-point coverage, and risk interception, effectively mitigating the high costs and subjectivity of human grading. Experimental results demonstrate that the generated rubrics achieve a 91.8% concordance rate with clinical expert blind audits, establishing highly dependable medical reliability. Crucially, baseline evaluations on this benchmark reveal significant performance disparities among state-of-the-art models when navigating real-world clinical nuances, highlighting the limitations of conventional exam-based metrics. Ultimately, QuarkMedBench establishes a rigorous, reproducible yardstick for measuring LLM performance on complex health issues, while its framework inherently supports dynamic knowledge updates to prevent benchmark obsolescence.

Yao Wu, Kangping Yin, Liang Dong +13

Quark Medical Team, Alibaba Group

LLM Evaluation Clinical Language Model Evaluation Medical LLMs Medical QA LLM Safety Evaluation LLM-as-a-Judge

Mar 13, 2026

Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities

Bibliographic reference extraction and parsing are foundational for citation indexing, linking, and downstream scholarly knowledge-graph construction. However, most established evaluations focus on clean, English, end-of-document bibliographies, and therefore underrepresent the Social Sciences and Humanities (SSH), where citations are frequently multilingual, embedded in footnotes, abbreviated, and shaped by heterogeneous historical conventions. We present a unified benchmark that targets these SSH-realistic conditions across three complementary datasets: CEX (English journal articles spanning multiple disciplines), EXCITE (German/English documents with end-section, footnote-only, and mixed regimes), and LinkedBooks (humanities references with strong stylistic variation and multilinguality). We evaluate three tasks of increasing difficulty -- reference extraction, reference parsing, and end-to-end document parsing -- under a schema-constrained setup that enables direct comparison between a strong supervised pipeline baseline (GROBID) and contemporary LLMs (DeepSeek-V3.1, Mistral-Small-3.2-24B, Gemma-3-27B-it, and Qwen3-VL (4B-32B variants)). Across datasets, extraction largely saturates beyond a moderate capability threshold, while parsing and end-to-end parsing remain the primary bottlenecks due to structured-output brittleness under noisy layouts. We further show that lightweight LoRA adaptation yields consistent gains -- especially on SSH-heavy benchmarks -- and that segmentation/pipelining can substantially improve robustness. Finally, we argue for hybrid deployment via routing: leveraging GROBID for well-structured, in-distribution PDFs while escalating multilingual and footnote-heavy documents to task-adapted LLMs.

Yurui Zhu, Giovanni Colavizza, Matteo Romanello

Odoma LLC

Document Information Extraction LLM Information Extraction LLM Evaluation Multilingual Language Model Evaluation LLM Fine-Tuning

Mar 13, 2026

Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models

While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require understanding distributional information, such as population-level trends and preferences expressed across collections of text. We introduce Text2DistBench, a reading comprehension benchmark for evaluating LLMs' ability to infer distributional knowledge from natural language. Built from real-world YouTube comments about movie and music entities, the benchmark provides models with entity metadata and associated comments, and requires them to answer distributional questions, such as estimating the proportions of positive and negative comments, or identifying the most and second most frequent topics discussed among viewers. To support reliable and long-term evaluation, the construction pipeline of Text2DistBench is fully automated and continuously updated to incorporate newly emerging entities over time. Experiments across multiple LLMs show that while models substantially outperform random baselines, performance varies widely across different distribution types and characteristics. These findings highlight both the capabilities and limitations of current LLMs in distributional reading comprehension and demonstrate the value of Text2DistBench as a practical and scalable testbed for future research.

Pei-Fu Guo, Ya-An Tsai, Chun-Chia Hsu +6

National Taiwan University · University of California, Los Angeles · Academia Sinica, Taiwan +1

Mar 13, 2026

Developing the PsyCogMetrics AI Lab to Evaluate Large Language Models and Advance Cognitive Science -- A Three-Cycle Action Design Science Study

This study presents the development of the PsyCogMetrics AI Lab (psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometric and cognitive-science methodologies for Large Language Model (LLM) evaluation. Framed as a three-cycle Action Design Science study, the Relevance Cycle identifies key limitations in current evaluation methods and unfulfilled stakeholder needs. The Rigor Cycle draws on kernel theories such as Popperian falsifiability, Classical Test Theory, and Cognitive Load Theory to derive deductive design objectives. The Design Cycle operationalizes these objectives through nested Build-Intervene-Evaluate loops. The study contributes a novel IT artifact, a validated design for LLM evaluation, benefiting research at the intersection of AI, psychology, cognitive science, and the social and behavioral sciences.

Zhiye Jin, Yibai Li, K. D. Joshi +4

Nancy · Marywood University · The University of Scranton +3

LLM Evaluation Psychometric Validation

Mar 13, 2026

Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks

Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approach controls for task familiarity by giving each model task-relevant training before evaluation, originally through supervised finetuning. However, suitable training data is often hard to come by, and evaluation results vary with the data chosen. In this paper, we propose a two-stage test-time reinforcement learning (RL) alignment method for train-before-test. First, RL with a single sample provides a first alignment of the model to the task format, and second, test-time RL with majority-voting reward aligns the model to the benchmark distribution. Our test-time RL alignment method aligns similarly well as SFT-based train-before test, but without requiring a task-specific training set. On a domain-specific benchmark without training data, we show that direct evaluation underestimates base models which perform substantially better once aligned, yielding a more faithful evaluation of their capabilities. Moreover, for reasoning tasks, the performance gap between fine-tuned models and their base models largely disappears after alignment, suggesting that many gains from RLVR/SFT reported in the literature are not a difference in reasoning capability, but rather artifacts of task familiarity.

Kun Wang, Reinhard Heckel

School of Computation, Information and Technology, Technical University of Munich · Munich Center for Machine Learning

LLM Evaluation Inference-Time Language Model Alignment Test-Time RL RL for Language Model Reasoning

Mar 13, 2026

CLARIN-PT-LDB: An Open LLM Leaderboard for Portuguese to assess Language, Culture and Civility

This paper reports on the development of a leaderboard of Open Large Language Models (LLM) for European Portuguese (PT-PT), and on its associated benchmarks. This leaderboard comes as a way to address a gap in the evaluation of LLM for European Portuguese, which so far had no leaderboard dedicated to this variant of the language. The paper also reports on novel benchmarks, including some that address aspects of performance that so far have not been available in benchmarks for European Portuguese, namely model safeguards and alignment to Portuguese culture. The leaderboard is available at https://huggingface.co/spaces/PORTULAN/portuguese-llm-leaderboard.

João Silva, Luís Gomes, António Branco

University of Lisbon NLX—Grupo de Fala e Linguagem Natural, Departmento de Informática Faculdade de Ciências, Campo Grande, 1749-016 Lisboa, Portugal

LLM Evaluation Portuguese Language Models Cross-Cultural Language Model Evaluation LLM Safety Benchmarks LLM Alignment

Mar 12, 2026

LLM BiasScope: A Real-Time Bias Analysis Platform for Comparative LLM Evaluation

As large language models (LLMs) are deployed widely, detecting and understanding bias in their outputs is critical. We present LLM BiasScope, a web application for side-by-side comparison of LLM outputs with real-time bias analysis. The system supports multiple providers (Google Gemini, DeepSeek, MiniMax, Mistral, Meituan, Meta Llama) and enables researchers and practitioners to compare models on the same prompts while analyzing bias patterns. LLM BiasScope uses a two-stage bias detection pipeline: sentence-level bias detection followed by bias type classification for biased sentences. The analysis runs automatically on both user prompts and model responses, providing statistics, visualizations, and detailed breakdowns of bias types. The interface displays two models side-by-side with synchronized streaming responses, per-model bias summaries, and a comparison view highlighting differences in bias distributions. The system is built on Next.js with React, integrates Hugging Face inference endpoints for bias detection, and uses the Vercel AI SDK for multi-provider LLM access. Features include real-time streaming, export to JSON/PDF, and interactive visualizations (bar charts, radar charts) for bias analysis. LLM BiasScope is available as an open-source web application, providing a practical tool for bias evaluation and comparative analysis of LLM behaviour.

Himel Ghosh, Nick Elias Werner

Technical University of Munich, Germany · Sapienza University of Rome, Italy

Language Model Bias Evaluation LLM Evaluation LLM Auditing

Mar 12, 2026

When LLM Judge Scores Look Good but Best-of-N Decisions Fail

Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels. This can be misleading when the real deployment task is best-of-n selection within a prompt. In a 5,000-prompt best-of-4 benchmark from Chatbot Arena, a judge with moderate global correlation (r = 0.47) captures only 21.0% of the improvement that perfect selection would achieve over random choice. The gap arises because global agreement is driven largely by prompt-level baseline effects, while selection depends on within-prompt ranking: within-prompt correlation is only r_within = 0.27, and coarse pointwise scoring creates ties in 67% of pairwise comparisons. In a matched-pair best-of-2 audit, explicit pairwise judging recovers much of this lost signal, raising recovery from 21.1% to 61.2%. For judge-based selection, the relevant audit should report within-prompt signal, tie rates, and recovery/top-1 accuracy, not global agreement alone.

Eddie Landesberg

LLM Evaluation LLM-as-a-Judge Best-of-N Sampling LLM Reranking

Mar 12, 2026

Agreement Between Large Language Models, Human Reviewers, and Authors in Evaluating STROBE Checklists for Observational Studies in Rheumatology

Introduction: Evaluating compliance with the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement can be time-consuming and subjective. This study compares STROBE assessments from large language models (LLMs), a human reviewer panel, and the original manuscript authors in observational rheumatology research. Methods: Guided by the GRRAS and DEAL Pathway B frameworks, 17 rheumatology articles were independently assessed. Evaluations used the 22-item STROBE checklist, completed by the authors, a five-person human panel (ranging from junior to senior professionals), and two LLMs (ChatGPT-5.2, Gemini-3Pro). Items were grouped into Methodological Rigor and Presentation and Context domains. Inter-rater reliability was calculated using Gwet's Agreement Coefficient (AC1). Results: Overall agreement across all reviewers was 85.0% (AC1=0.826). Domain stratification showed almost perfect agreement for Presentation and Context (AC1=0.841) and substantial agreement for Methodological Rigor (AC1=0.803). Although LLMs achieved complete agreement (AC1=1.000) with all human reviewers on standard formatting elements, their agreement with human reviewers and authors declined on complex items. For example, regarding the item on loss to follow-up, the agreement between Gemini 3 Pro and the senior reviewer was AC1=-0.252, while the agreement with the authors was only fair. Additionally, ChatGPT-5.2 generally demonstrated higher agreement with human reviewers than Gemini-3Pro on specific methodological items. Conclusion: While LLMs show potential for basic STROBE screening, their lower agreement with human experts on complex methodological items likely reflects a reliance on surface-level information. Currently, these models appear more reliable for standardizing straightforward checks than for replacing expert human judgment in evaluating observational research.

Emre Bilgin, Ebru Ozturk, Meera Shah +6

Sakarya University, Faculty of Medicine, Department of Internal Medicine, Division of Rheumatology, Sakarya, Turkiye · Topiwala NaBonal Medical College and B.Y.L. Nair Hospital, Department of Rheumatology, , Mumbai, India · St Luke’s Medical Center (Global City), Philippines +9

LLM Evaluation Healthcare Human-in-the-Loop Evaluation

Mar 12, 2026

Language Model Teams as Distributed Systems

Large language models (LLMs) are growing increasingly capable, prompting recent interest in LLM teams. Yet, despite increased deployment of LLM teams at scale, we lack a principled framework for addressing key questions such as when a team is helpful, how many agents to use, how structure impacts performance -- and whether a team is better than a single agent. Rather than designing and testing these possibilities through trial-and-error, we propose using distributed systems as a principled foundation for creating and evaluating LLM teams. We find that many of the fundamental advantages and challenges studied in distributed computing also arise in LLM teams, highlighting the rich practical insights that can come from the cross-talk of these two fields of study.

Elizabeth Mieczkowski, Katherine M. Collins, Ilia Sucholutsky +2

Princeton University · Massachusetts Institute of Technology · University of Cambridge +1

Multi-Agent LLM Systems Multi-LLM Collaboration LLM Evaluation

Mar 12, 2026

Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions

Large language models struggle to catch errors in their own outputs when the review happens in the same session that produced them. This paper introduces Cross-Context Review (CCR), a straightforward method where the review is conducted in a fresh session with no access to the production conversation history. We ran a controlled experiment: 30 artifacts (code, technical documents, presentation scripts) with 150 injected errors, tested under four review conditions -- same-session Self-Review (SR), repeated Self-Review (SR2), context-aware Subagent Review (SA), and Cross-Context Review (CCR). The central result is that a second review helps only when it happens in a fresh session: CCR (F1 28.6%) outperforms a second review in the same session (SR2, 21.7%) robustly, both in the first run (paired t, p<0.001) and in the three-run average (Holm-adjusted p=0.004). This version updates the broader comparisons. Averaged across runs, and excluding one SR run whose records could not be verified, CCR is not significantly ahead of context-aware subagent review (SA, 23.8%; p=0.057) or of a single same-session review (SR, 27.1%; p=0.26); the first version's advantages over these two baselines came from run 1. CCR needs no infrastructure and costs one extra session.

Tae-Eun Song

Daejeon Jungang Cheonggua Co., Ltd.

LLM Self-Correction LLM Evaluation

Mar 12, 2026

To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times

Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions, that correlate with human judgments. These estimates are obtained by prompting an LLM, in zero-shot fashion, with a question similar to those used in human studies. Meanwhile, for other norms such as lexical decision time or age of acquisition, LLMs require supervised fine-tuning to obtain results that align with ground-truth values. In this paper, we extend this approach to the previously unstudied features of sentence memorability and reading times, which involve the relationship between multiple words in a sentence-level context. Our results show that via fine-tuning, models can provide estimates that correlate with human-derived norms and exceed the predictive power of interpretable baseline predictors, demonstrating that LLMs contain useful information about sentence-level features. At the same time, our results show very mixed zero-shot and few-shot performance, providing further evidence that care is needed when using LLM-prompting as a proxy for human cognitive measures.

Thomas Hikaru Clark, Carlos Arriaga, Javier Conde +2

Massachusetts Institute of Technology · Universidad Politécnica de Madrid

Mar 12, 2026

BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs

Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation by matching texts directly to human-readable label descriptions. While early approaches have predominantly relied on cross-encoder models fine-tuned for natural language inference (NLI), recent advances in text-embedding models, rerankers, and instruction-tuned large language models (LLMs) have challenged the dominance of NLI-based architectures. Yet, systematically comparing these diverse approaches remains difficult. Existing evaluations, such as MTEB, often incorporate labeled examples through supervised probes or fine-tuning, leaving genuine zero-shot capabilities underexplored. To address this, we introduce BTZSC, a comprehensive benchmark of 22 public datasets spanning sentiment, topic, intent, and emotion classification, capturing diverse domains, class cardinalities, and document lengths. Leveraging BTZSC, we conduct a systematic comparison across four major model families, NLI cross-encoders, embedding models, rerankers and instruction-tuned LLMs, encompassing 38 public and custom checkpoints. Our results show that: (i) modern rerankers, exemplified by Qwen3-Reranker-8B, set a new state-of-the-art with macro F1 = 0.72; (ii) strong embedding models such as GTE-large-en-v1.5 substantially close the accuracy gap while offering the best trade-off between accuracy and latency; (iii) instruction-tuned LLMs at 4--12B parameters achieve competitive performance (macro F1 up to 0.67), excelling particularly on topic classification but trailing specialized rerankers; (iv) NLI cross-encoders plateau even as backbone size increases; and (v) scaling primarily benefits rerankers and LLMs over embedding models. BTZSC and accompanying evaluation code are publicly released to support fair and reproducible progress in zero-shot text understanding.

Ilias Aarab

European Central Bank, Frankfurt am Main, Germany

Zero-Shot Text Classification LLM Evaluation Text Embedding Models

Mar 12, 2026

Large Language Models for Biomedical Article Classification

This work presents a systematic and in-depth investigation of the utility of large language models as text classifiers for biomedical article classification. The study uses several small and mid-size open source models, as well as selected closed source ones, and is more comprehensive than most prior work with respect to the scope of evaluated configurations: different types of prompts, output processing methods for generating both class and class probability predictions, as well as few-shot example counts and selection methods. The performance of the most successful configurations is compared to that of conventional classification algorithms. The obtained average PR AUC over 15 challenging datasets above 0.4 for zero-shot prompting and nearly 0.5 for few-shot prompting comes close to that of the naïve Bayes classifier (0.5), the random forest algorithm (0.5 with default settings or 0.55 with hyperparameter tuning) and fine-tuned transformer models (0.5). These results confirm the utility of large language models as text classifiers for non-trivial domains and provide practical recommendations of the most promising setups, including in particular using output token probabilities for class probability prediction.

Jakub Proboszcz, Paweł Cichosz

Institute of Computer Science, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland

Few-Shot Text Classification Large Language Model-Based Text Classification Text Classification Classification LLM Evaluation Zero-Shot Text Classification+1

Mar 12, 2026

SemBench: A Universal Semantic Framework for LLM Evaluation

Recent progress in Natural Language Processing (NLP) has been driven by the emergence of Large Language Models (LLMs), which exhibit remarkable generative and reasoning capabilities. However, despite their success, evaluating the true semantic understanding of these models remains a persistent challenge. Traditional benchmarks such as Word-in-Context (WiC) effectively probe this capability, but their creation is resource-intensive and often limited to high-resource languages. In this paper, we introduce SemBench, a framework for automatically generating synthetic benchmarks that assess the semantic competence of LLMs using only dictionary sense definitions and a sentence encoder. This approach eliminates the need for curated example sentences, making it both scalable and language-independent. We evaluate SemBench in three languages (English, Spanish, and Basque) spanning different levels of linguistic resources, and across a wide range of LLMs. Our results show that rankings derived from SemBench strongly correlate with those obtained from standard WiC datasets. Furthermore, our analysis demonstrates that only a small number of examples is required to achieve stable and meaningful rankings. Overall, SemBench provides a lightweight, adaptable, and data-efficient framework for cross-lingual evaluation of semantic understanding in LLMs.

Mikel Zubillaga, Naiara Perez, Oscar Sainz +1

HiTZ Center - Ixa, University of the Basque Country UPV/EHU

LLM Evaluation Multilingual Language Model Evaluation Synthetic Data Generation for Language Models

Mar 11, 2026

Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation

The ability to rigorously estimate the failure rates of large language models (LLMs) is a prerequisite for their safe deployment. Currently, however, practitioners often face a tradeoff between expensive human gold standards and potentially severely-biased automatic annotation schemes such as "LLM-as-a-Judge" labeling. In this paper, we propose a new, practical, and efficient approach to LLM failure rate estimation based on constrained maximum-likelihood estimation (MLE). Our method integrates three distinct signal sources: (i) a small, high-quality human-labeled calibration set, (ii) a large corpus of LLM-judge annotations, and, most importantly, (iii) additional side information via domain-specific constraints derived from known bounds on judge performance statistics. We validate our approach through a comprehensive empirical study, benchmarking it against state-of-the-art baselines like Prediction-Powered Inference (PPI). Across diverse experimental regimes -- spanning varying judge accuracies, calibration set sizes, and LLM failure rates -- our constrained MLE consistently delivers more accurate and lower-variance estimates than existing methods. By moving beyond the "black-box" use of automated judges to a flexible framework, we provide a principled, interpretable, and scalable pathway towards LLM failure-rate certification.

Minghe Shen, Ananth Balashankar, Adam Fisch +2

University College London · Google DeepMind

LLM Reliability LLM Evaluation

Mar 11, 2026

Temporal Text Classification with Large Language Models

Languages change over time. Computational models can be trained to recognize such changes enabling them to estimate the publication date of texts. Despite recent advancements in Large Language Models (LLMs), their performance on automatic dating of texts, also known as Temporal Text Classification (TTC), has not been explored. This study provides the first systematic evaluation of leading proprietary (Claude 3.5, GPT-4o, Gemini 1.5) and open-source (LLaMA 3.2, Gemma 2, Mistral, Nemotron 4) LLMs on TTC using three historical corpora, two in English and one in Portuguese. We test zero-shot and few-shot prompting, and fine-tuning settings. Our results indicate that proprietary models perform well, especially with few-shot prompting. They also indicate that fine-tuning substantially improves open-source models but that they still fail to match the performance delivered by proprietary LLMs.

Nishat Raihan, Marcos Zampieri

George Mason University, Fairfax, VA, USA

Text Classification Large Language Model-Based Text Classification LLM Evaluation

Mar 11, 2026

AI Psychometrics: Evaluating the Psychological Reasoning of Large Language Models with Psychometric Validities

The immense number of parameters and deep neural networks make large language models (LLMs) rival the complexity of human brains, which also makes them opaque ``black box'' systems that are challenging to evaluate and interpret. AI Psychometrics is an emerging field that aims to tackle these challenges by applying psychometric methodologies to evaluate and interpret the psychological traits and processes of artificial intelligence (AI) systems. This paper investigates the application of AI Psychometrics to evaluate the psychological reasoning and overall psychometric validity of four prominent LLMs: GPT-3.5, GPT-4, LLaMA-2, and LLaMA-3. Using the Technology Acceptance Model (TAM), we examined convergent, discriminant, predictive, and external validity across these models. Our findings reveal that the responses from all these models generally met all validity criteria. Moreover, higher-performing models like GPT-4 and LLaMA-3 consistently demonstrated superior psychometric validity compared to their predecessors, GPT-3.5 and LLaMA-2. These results help to establish the validity of applying AI Psychometrics to evaluate and interpret large language models.

Yibai Li, Xiaolin Lin, Zhenghui Sha +2

The University of Scranton · California State University, Sacramento · The University of Texas at Austin +1

LLM Evaluation Psychometric Validation

Mar 11, 2026

Ranking Reasoning LLMs under Test-Time Scaling

Test-time scaling evaluates reasoning LLMs by sampling multiple outputs per prompt, but ranking models in this regime remains underexplored. We formalize dense benchmark ranking under test-time scaling and introduce Scorio, a library that implements statistical ranking methods such as paired-comparison models, item response theory (IRT) models, voting rules, and graph- and spectral-based methods. Across

20

reasoning models on four Olympiad-style math benchmarks (AIME'24, AIME'25, HMMT'25, and BrUMO'25; up to

N=80

trials), most full-trial rankings agree closely with the Bayesian gold standard

\mathrm{Bayes}_{\mathcal{U}}@80

(mean Kendall's

τ_b = 0.93

--

0.95

), and

19

--

34

methods recover exactly the same ordering. In the single-trial regime, the best methods reach

τ_b \approx 0.86

. Using greedy decoding as an empirical prior (

\mathrm{Bayes}_{\mathbf{R}_0}@N

) reduces variance at

N=1

by

16

--

52\%

, but can bias rankings when greedy and stochastic sampling disagree. These results identify reliable ranking methods for both high- and low-budget test-time scaling. We release Scorio as an open-source library at https://github.com/mohsenhariri/scorio.

Mohsen Hariri, Michael Hinczewski, Jing Ma +1

Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH, USA · Department of Physics, Case Western Reserve University, Cleveland, OH, USA

LLM Evaluation Test-Time Scaling

Mar 11, 2026

Making Bielik LLM Reason (Better): A Field Report

This paper presents a research program dedicated to evaluating and advancing the reasoning capabilities of Bielik, a Polish large language model. The study describes a number of stages of work: initial benchmarking and creation of evaluation methodology, analyzing of comparative results with other LLMs and outlining of future prospects that take into account the limitations of the analyses conducted so far and aims to keep Bielik in the race give the ever-changing -- and competitive -- AI landscape.

Adam Trybus, Bartosz Bartnicki, Remigiusz Kinas

Institute of Philosophy, Jagiellonian University, 52 Grodzka St., Kraków 31-044, Poland · Bielik.ai (Speakleash Foundation), 33/4 Niemczańska St., Wrocław 50-561, Poland

LLM Reasoning Language Modeling LLM Evaluation

Mar 11, 2026

PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses. PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, coherence, relevance, objectivity, clarity, conciseness), and uses an LLM-based evaluator to output (i) scalar scores on a 1-5 Likert scale and (ii) criterion-specific natural-language rationales grounded in the rubric. Across 7 benchmarks and 5 task models, PEEM's accuracy axis strongly aligns with conventional accuracy while preserving model rankings (aggregate Spearman rho about 0.97, Pearson r about 0.94, p < 0.001). A multi-evaluator study with four models shows consistent relative judgments (pairwise rho = 0.68-0.85), supporting evaluator-agnostic deployment. Beyond alignment, PEEM captures complementary linguistic failure modes and remains informative under prompt perturbations: prompt-quality trends track downstream accuracy under iterative rewrites, semantic adversarial manipulations induce clear score degradation, and meaning-preserving paraphrases yield high stability (robustness rate about 76.7-80.6%). Finally, using only PEEM scores and rationales as feedback, a zero-shot prompt rewriting loop improves downstream accuracy by up to 11.7 points, outperforming supervised and RL-based prompt-optimization baselines. Overall, PEEM provides a reproducible, criterion-driven protocol that links prompt formulation to response behavior and enables systematic diagnosis and optimization of LLM interactions.

Minki Hong, Eunsoo Lee, Sohyun Park +1

Department of Computer Science and Artificial Intelligence, Dongguk University, South Korea

LLM Prompting LLM Evaluation Prompt Optimization LLM-as-a-Judge

Mar 11, 2026

Brevity Constraints Reverse Performance Hierarchies in Language Models

Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller ones by 28.4 percentage points despite 10-100x more parameters. Through systematic evaluation of 31 models (0.5B-405B parameters) across 1,485 problems, we identify the mechanism as spontaneous scale-dependent verbosity that introduces errors through overelaboration. Causal intervention experiments demonstrate this reflects correctable prompt design rather than fundamental capability limitations. Constraining large models to produce brief responses improves accuracy by 26 percentage points and reduces performance gaps by up to two-thirds. Most critically, brevity constraints completely reverse performance hierarchies on mathematical reasoning and scientific knowledge benchmarks, with large models achieving 7.7-15.9 percentage point advantages over small models -- direct inversions of the original gaps. These reversals prove large models possess superior latent capabilities that universal prompting masks. We validate findings through three independent contamination tests and demonstrate inverse scaling operates continuously across the full parameter spectrum, with dataset-specific optimal scales ranging from 0.5B to 3.0B parameters. Our results establish that maximizing large model performance requires scale-aware prompt engineering rather than universal evaluation protocols, with immediate implications for deployment: prompt adaptation simultaneously improves accuracy and reduces computational costs.

MD Azizul Hakim

Department of Computer Science Bangladesh Sweden Polytechnic Institute Chattogram, Bangladesh

LLM Evaluation Language Model Scaling Language Model Scaling Laws

Mar 11, 2026

Evaluating Digital Inclusiveness of Digital Agri-Food Tools Using Large Language Models: A Comparative Analysis Between Human and AI-Based Evaluations

Ensuring digital inclusiveness is a critical priority in agri-food systems, particularly in the Global South, where digital divides persist. The Multidimensional Digital Inclusiveness Index (MDII) offers a comprehensive, human-led framework to assess how inclusive digital agricultural tools (agritools) are. However, the current evaluation process is resource intensive, often requiring months to complete. This study explores whether large language models (LLMs) can support a rapid, AI-enabled assessment of digital inclusiveness, complementing the MDII's existing workflow. Using a comparative analysis, the research benchmarks the performance of four LLMs (Grok, Gemini, GPT-4o, and GPT-5) against prior expert-led evaluations. The study investigates model alignment with human scores, sensitivity to temperature settings, and potential sources of bias. Findings suggest that LLMs can generate evaluative outputs that approximate expert judgment in some dimensions, though reliability varies across models and contexts. This exploratory work provides early evidence for the integration of GenAI into inclusive digital development monitoring, with implications for scaling evaluations in time-sensitive or resource-constrained environments.

Githma Pewinya, Carolina Martins, Garcia Mariangel

Colombo, Sri Lanka · International Water Management Institute

LLM Reliability LLM Evaluation

Mar 11, 2026

Large language models can disambiguate opioid slang on social media

Social media text shows promise for monitoring trends in the opioid overdose crisis; however, the overwhelming majority of social media text is unrelated to opioids. When leveraging social media text to monitor trends in the ongoing opioid overdose crisis, a common strategy for identifying relevant content is to use a lexicon of opioid-related terms as inclusion criteria. However, many slang terms for opioids, such as "smack" or "blues," have common non-opioid meanings, making them ambiguous. The advanced textual reasoning capability of large language models (LLMs) presents an opportunity to disambiguate these slang terms at scale. We present three tasks on which to evaluate four state-of-the-art LLMs (GPT-4, GPT-5, Gemini 2.5 Pro, and Claude Sonnet 4.5): a lexicon-based setting, in which the LLM must disambiguate a specific term within the context of a given post; a lexicon-free setting, in which the LLM must identify opioid-related posts from context without a lexicon; and an emergent slang setting, in which the LLM must identify opioid-related posts with simulated new slang terms. All four LLMs showed excellent performance across all tasks. In both subtasks of the lexicon-based setting, LLM F1 scores ("fenty" subtask: 0.824-0.972; "smack" subtask: 0.540-0.862) far exceeded those of the best lexicon strategy (0.126 and 0.009, respectively). In the lexicon-free task, LLM F1 scores (0.544-0.769) surpassed those of lexicons (0.080-0.540), and LLMs demonstrated uniformly higher recall. On emergent slang, all LLMs had higher accuracy (average: 0.784), F1 score (average: 0.712), precision (average: 0.981), and recall (average: 0.587) than the two lexicons assessed. Our results show that LLMs can be used to identify relevant content for low-prevalence topics, including but not limited to opioid references, enhancing data provided to downstream analyses and predictive models.

Kristy A. Carpenter, Issah A. Samori, Mathew V. Kiang +4

Departments of 1Biomedical Data Science, Stanford University, Stanford, CA 94305, USA · Departments of 2Bioengineering, Stanford University, Stanford, CA 94305, USA · Departments of 3Epidemiology and Population Health, Stanford University, Stanford, CA 94305, USA +5

Word Sense Disambiguation Social Media Analysis LLM Evaluation

Mar 11, 2026

Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

Judging the novelty of research ideas is crucial for advancing science, enabling the identification of unexplored directions, and ensuring contributions meaningfully extend existing knowledge rather than reiterate minor variations. However, given the exponential growth of scientific literature, manually judging the novelty of research ideas through literature reviews is labor-intensive, subjective, and infeasible at scale. Therefore, recent efforts have proposed automated approaches for research idea novelty judgment. Yet, evaluation of these approaches remains largely inconsistent and is typically based on non-standardized human evaluations, hindering large-scale, comparable evaluations. To address this, we introduce RINoBench, the first comprehensive benchmark for large-scale evaluation of research idea novelty judgments. It comprises 1,381 research ideas derived from and judged by human experts as well as nine automated evaluation metrics designed to assess both rubric-based novelty scores and textual justifications of novelty judgments. Using this benchmark, we evaluate several state-of-the-art large language models (LLMs) on their ability to judge the novelty of research ideas. Our findings reveal that while LLM-generated reasoning closely mirrors human rationales, this alignment does not reliably translate into accurate novelty judgments, which diverge significantly from human gold standard judgments - even among leading reasoning-capable models. Data and code available at: https://github.com/TimSchopf/RINoBench.

Tim Schopf, Michael Färber

TU Dresden & ScaDS.AI Dresden/Leipzig, Germany · National Institute of Informatics, Tokyo, Japan

Automated Evaluation LLM-as-a-Judge LLM Evaluation

Mar 10, 2026

Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling

Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of risk: operational failures arising from repeated generations of the same prompt rather than broad task generalization. In high-stakes settings, response consistency and safety under repeated use are critical operational requirements. We introduce Accelerated Prompt Stress Testing (APST), a depth-oriented evaluation framework inspired by highly accelerated stress testing in reliability engineering. APST probes LLM behavior by repeatedly sampling identical prompts under controlled operational conditions, including temperature variation and prompt perturbation, to surface latent failure modes such as hallucinations, refusal inconsistency, and unsafe completions. Rather than treating failures as isolated events, APST characterizes them statistically as stochastic outcomes of repeated inference. We model observed safety failures using Bernoulli and binomial formulations to estimate per-inference failure probabilities, enabling quantitative comparison of operational risk across models and configurations. We apply APST to multiple instruction-tuned LLMs evaluated on AIR-BENCH 2024 derived safety and security prompts. While models exhibit similar performance under conventional single- or very-low-sample evaluation (N <= 3), repeated sampling reveals substantial variation in empirical failure probabilities across temperatures. These results demonstrate that shallow benchmark scores can obscure meaningful differences in reliability under sustained use.

Keita Broadwater

Independent Researcher, San Jose, USA

LLM Evaluation Language Model Safety Evaluation LLM Reliability LLM Safety Benchmarks

Mar 10, 2026

CREATE: Testing LLMs for Associative Creativity

A key component of creativity is associative reasoning: the ability to draw novel yet meaningful connections between concepts. We introduce CREATE, a benchmark designed to evaluate models' capacity for creative associative reasoning. CREATE requires models to generate sets of paths connecting concepts in a model's parametric knowledge. Paths should have high specificity (distinctiveness and closeness of the concept connection) and high diversity (dissimilarity from other paths), and models are scored more highly if they produce a larger set of strong, diverse paths. This task shares demands of real creativity tasks like hypothesis generation, including an extremely large search space, but enables collection of a sizable benchmark with objective answer grading. Evaluation of frontier models shows that the strongest models achieve higher creative utility than others, with the high multiplicity of answers and complexity of the search making benchmark saturation difficult to achieve. Furthermore, our results illustrate that thinking models are not always more effective on our task, even with high token budgets. Recent approaches for creative prompting give some but limited additional improvement. CREATE provides a sandbox for developing new methods to improve models' capacity for associative creativity.

Manya Wadhwa, Tiasa Singha Roy, Harvey Lederman +2

New York University · The University of Texas at Austin

Creativity Assessment Computational Creativity LLM Evaluation

Mar 10, 2026

One-Eval: An Agentic System for Automated and Traceable LLM Evaluation

Reliable evaluation is essential for developing and deploying large language models, yet in practice it often requires substantial manual effort: practitioners must identify appropriate benchmarks, reproduce heterogeneous evaluation codebases, configure dataset schema mappings, and interpret aggregated metrics. To address these challenges, we present One-Eval, an agentic evaluation system that converts natural-language evaluation requests into executable, traceable, and customizable evaluation workflows. One-Eval integrates (i) NL2Bench for intent structuring and personalized benchmark planning, (ii) BenchResolve for benchmark resolution, automatic dataset acquisition, and schema normalization to ensure executability, and (iii) Metrics & Reporting for task-aware metric selection and decision-oriented reporting beyond scalar scores. The system further incorporates human-in-the-loop checkpoints for review, editing, and rollback, while preserving sample evidence trails for debugging and auditability. Experiments show that One-Eval can execute end-to-end evaluations from diverse natural-language requests with minimal user effort, supporting more efficient and reproducible evaluation in industrial settings. Our framework is publicly available at https://github.com/OpenDCAI/One-Eval.

Chengyu Shen, Yanheng Hou, Minghui Pan +8

Peking University · Beijing Institute of Technology · Beijing University of Posts and Telecommunications +1

Automated Evaluation LLM Evaluation Agent Evaluation

Mar 10, 2026

EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages

Large language models achieve near-ceiling performance on code generation benchmarks, yet most of the programming languages used by popular benchmarks such as SWE-bench and HumanEval (e.g. Python, JavaScript) are squarely in-distribution. They appear at scale in pre-training corpora and are heavily reinforced during post-training. To study LLM performance on unfamiliar programming languages, we introduce EsoLang-Bench, a benchmark using five esoteric programming languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare). All five of our chosen esoteric languages are Turing-complete, so the same algorithmic problems that are solvable in Python or JavaScript are in principle solvable in each of them. Yet, they are unfamiliar to LLMs which makes them a good proxy for evaluating out-of-distribution performance. The unfamiliarity of esoteric languages comprises of: (i) the hard-by-design primitives comprising the language; (ii) substantially less representation in pre-training corpora (340x to over 60,000x fewer public GitHub repositories than Python); (iii) negligible deployment value, which makes targeted inclusion in post-training data economically irrational. We evaluate five frontier models across five prompting strategies and find a dramatic capability gap. The same 80 problems expressed in Python or JavaScript reach 100% accuracy on top frontier models, while the equivalent esoteric versions score only 0-11%. Few-shot learning and self-reflection also fail to close this gap. EsoLang-Bench therefore provides a contamination-resistant testbed for measuring how well frontier models generalise algorithmic problem-solving to programming languages outside their training distribution.

Aman Sharma, Paras Chopra

Lossfunk

LLM Evaluation LLM Code Generation OOD Generalization Code Generation