LLM Evaluation

LLM: Large Language Model

Overview

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

2,539 papers144 papers in the last four weeks, down 56% on the four weeks before. 1.1% of all new papers.

Oct 28, 2025

Idea2Plan: Exploring AI-Powered Research Planning

Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields. In this work, we investigate how LLMs can handle the transition from conceptual research ideas to well-structured research plans. Effective research planning not only supports scientists in advancing their research but also represents a crucial capability for the development of autonomous research agents. Despite its importance, the field lacks a systematic understanding of LLMs' research planning capability. To rigorously measure this capability, we introduce the Idea2Plan task and Idea2Plan Bench, a set of benchmarks built from ICML 2025 and Nature Mental Health papers released after major LLM training cutoffs. Each benchmark instance includes a research idea and a grading rubric capturing the key components of valid plans. We further propose Idea2Plan JudgeEval, a complementary benchmark to assess the reliability of LLM-based judges against expert annotations. Experimental results show that GPT-5 achieves the strongest performance on the benchmark, though substantial headroom remains for improvement. Our study provides new insights into LLMs' capability for research planning and lays the groundwork for future progress.
Oct 27, 2025

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar outputs. Yet scalable methods for evaluating LM output diversity remain limited, especially beyond narrow tasks such as random number or name generation, or beyond repeated sampling from a single model. We introduce Infinity-Chat, a large-scale dataset of 26K diverse, real-world, open-ended user queries that admit a wide range of plausible answers with no single ground truth. We introduce the first comprehensive taxonomy for characterizing the full spectrum of open-ended prompts posed to LMs, comprising 6 top-level categories (e.g., brainstorm & ideation) that further breaks down to 17 subcategories. Using Infinity-Chat, we present a large-scale study of mode collapse in LMs, revealing a pronounced Artificial Hivemind effect in open-ended generation of LMs, characterized by (1) intra-model repetition, where a single model consistently generates similar responses, and more so (2) inter-model homogeneity, where different models produce strikingly similar outputs. Infinity-Chat also includes 31,250 human annotations, across absolute ratings and pairwise preferences, with 25 independent human annotations per example. This enables studying collective and individual-specific human preferences in response to open-ended queries. Our findings show that LMs, reward models, and LM judges are less well calibrated to human ratings on model generations that elicit differing idiosyncratic annotator preferences, despite maintaining comparable overall quality. Overall, INFINITY-CHAT presents the first large-scale resource for systematically studying real-world open-ended queries to LMs, revealing critical insights to guide future research for mitigating long-term AI safety risks posed by the Artificial Hivemind.
Oct 26, 2025

Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks

Evaluating large language models (LLMs) typically requires thousands of benchmark items, making the process expensive, slow, and increasingly impractical at scale. Existing evaluation protocols rely on average accuracy over fixed item sets, treating all items as equally informative despite substantial variation in difficulty and discrimination. We introduce ATLAS, an adaptive testing framework based on Item Response Theory (IRT) that estimates model ability using Fisher information-guided item selection. ATLAS reduces the number of required items by up to 90% while maintaining measurement precision. For instance, it matches whole-bank ability estimates using only 41 items (0.157 MAE) on HellaSwag (5,600 items). We further reconstruct accuracy from ATLAS's ability estimates and find that reconstructed accuracies closely match raw accuracies across all five benchmarks, indicating that ability θθ preserves the global performance structure. At the same time, θθ provides finer discrimination within accuracy-equivalent models: among more than 3,000 evaluated models, 23-31% shift by more than 10 rank positions, and models with identical accuracies receive meaningfully different ability estimates. Code and calibrated item banks are available at https://github.com/Peiyu-Georgia-Li/ATLAS.git.
Oct 23, 2025

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health records). To evaluate LLMs' ability to identify and redact such information, prior work introduced real-life, scenario-based benchmarks (e.g., ConfAIde, PrivacyLens) and found that LLMs can leak private information in complex scenarios. However, these evaluations relied on proxy LLMs to judge the helpfulness and privacy-preservation quality of LLM responses, rather than directly measuring users' perceptions. To understand how users perceive the helpfulness and privacy-preservation quality of LLM responses to privacy-sensitive scenarios, we conducted a user study (n=94n=94) using 90 PrivacyLens scenarios. We found that users had low agreement with each other when evaluating identical LLM responses. In contrast, five proxy LLMs reached high agreement, yet each proxy LLM had low correlation with users' evaluations. These results indicate that proxy LLMs cannot accurately estimate users' wide range of perceptions of utility and privacy in privacy-sensitive scenarios. We discuss the need for more user-centered studies to measure LLMs' ability to help users while preserving privacy, and for improving alignment between LLMs and users in estimating perceived privacy and utility.
Oct 23, 2025

CS-54k: A Paper-Grounded Corpus and Benchmark for AI Research QA

Large language models (LLMs) are increasingly being used to support computer science research. To contribute reliably, these systems must be able to work with information distributed across research papers and across different aspects of the research process. However, large-scale resources that systematically organize such information into structured supervision for both model evaluation and post-training remain limited. To address this gap, we propose a systematic paper-to-QA construction pipeline that organizes information from AI research papers into structured QA pairs supported by source evidence. Using this pipeline, we construct CS-54k, a 54k-pair corpus derived from 14,474 openly licensed AI research papers. The corpus covers eight recurring paper components, including research domain, prior work, existing challenges, motivation, findings and assumptions, methods, experimental settings, and experimental results. We further derive two complementary subsets: CS-4k, a benchmark for evaluating LLMs on paper-derived research QA, and CS-50k, a companion corpus for post-training. Extensive evaluations on CS-4k reveal substantial performance differences across existing LLMs and paper components, with experimental settings and results remaining particularly challenging. Moreover, post-training on CS-50k substantially improves Qwen2.5-7B-Instruct on CS-4k, demonstrating the practical utility of structured, paper-derived supervision. Together, CS-4k and CS-50k provide a unified and scalable resource for benchmarking and improving LLMs on research paper question answering.
Oct 23, 2025

CreativityPrism: A Cross-Domain Evaluation Framework for Large Language Model Creativity

Creativity is often seen as a hallmark of human intelligence. While large language models(LLMs) are increasingly perceived as generating creative text, there is still no cross-domain and scalable framework to evaluate their creativity across diverse scenarios. Existing methods of LLM creativity evaluation either heavily rely on humans, limiting speed and scalability, or are fragmented across different domains and different definitions of creativity. To address this gap, we propose CreativityPrism, an evaluation and analysis framework that consolidates eight tasks from three domains: divergent thinking, creative writing, and logical reasoning, into a taxonomy of creativity that emphasizes three dimensions: quality, novelty, and diversity of LLM generations. The framework is designed to be scalable with reliable automatic evaluation judges that have been validated against human annotations. We evaluate 17 state-of-the-art (SoTA) LLMs on CreativityPrism and find that while frontier-scale LLMs dominate creative writing and logical reasoning tasks by a .10 (or 15%) lead over locally-deployable open models, they offer no significant advantage in divergent thinking, a domain much less explored in existing post-training regimes. Our analysis also shows that high performance in one creative dimension or domain rarely generalizes to others; specifically, novelty metrics often show weak or negative correlations with other metrics. This fragmentation confirms that a cross-domain, multi-dimensional framework like CreativityPrism is essential for any meaningful assessment of LLM creativity.
Oct 21, 2025

KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs

We present Korean SimpleQA (KoSimpleQA)\textbf{Korean SimpleQA (KoSimpleQA)}, a benchmark for evaluating factuality in large language models (LLMs) with a focus on Korean cultural knowledge. KoSimpleQA is designed to be challenging yet easy to grade, consisting of 938 short, fact-seeking questions with unambiguous answers. We conduct a comprehensive evaluation across a diverse set of open-source LLMs of varying sizes that support Korean, and find that even the strongest model generates correct answer only 31.6% of the time, underscoring the challenging nature of KoSimpleQA. Notably, performance rankings on KoSimpleQA differ substantially from those on the English SimpleQA, highlighting the unique value of our dataset. Furthermore, we observe that reasoning helps mitigate the cross-lingual knowledge gap in LLMs, which refers to disparities in their ability to manifest knowledge across languages. KoSimpleQA can be found at https://github.com/naver-ai/KoSimpleQA.
Oct 19, 2025

The Chameleon Nature of LLMs: Quantifying Multi-Turn Stance Instability in Search-Enabled Language Models

Integration of Large Language Models with search/retrieval engines has become ubiquitous, yet these systems harbor a critical vulnerability that undermines their reliability. We present the first systematic investigation of "chameleon behavior" in LLMs: their alarming tendency to shift stances when presented with contradictory questions in multi-turn conversations (especially in search-enabled LLMs). Through our novel Chameleon Benchmark Dataset, comprising 17,770 carefully crafted question-answer pairs across 1,180 multi-turn conversations spanning 12 controversial domains, we expose fundamental flaws in state-of-the-art systems. We introduce two theoretically grounded metrics: the Chameleon Score (0-1) that quantifies stance instability, and Source Re-use Rate (0-1) that measures knowledge diversity. Our rigorous evaluation of Llama-4-Maverick, GPT-4o-mini, and Gemini-2.5-Flash reveals consistent failures: all models exhibit severe chameleon behavior (scores 0.391-0.511), with GPT-4o-mini showing the worst performance. Crucially, small across-temperature variance (less than 0.004) suggests the effect is not a sampling artifact. Our analysis uncovers the mechanism: strong correlations between source re-use rate and confidence (r=0.627) and stance changes (r=0.429) are statistically significant (p less than 0.05), indicating that limited knowledge diversity makes models pathologically deferential to query framing. These findings highlight the need for comprehensive consistency evaluation before deploying LLMs in healthcare, legal, and financial systems where maintaining coherent positions across interactions is critical for reliable decision support.
Oct 18, 2025

BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction

Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physical constraints. While modern LLMs possess broad knowledge and strong reasoning capabilities that make them promising candidates for this domain, their construction competencies remain largely unevaluated. To address this gap, we introduce BuildArena, the first physics-aligned interactive benchmark designed for language-driven engineering construction. Technically, it contributes to the community in two aspects: (1) an extendable task design strategy spanning static and dynamic mechanics across multiple difficulty tiers; (2) a 3D Spatial Geometric Computation Library for supporting construction based on language instructions. On nine frontier LLMs and three additional open-weight models, BuildArena comprehensively evaluates their capabilities for language-driven and physics-grounded construction automation. We release the code at https://github.com/AI4Science-WestlakeU/BuildArena to benefit construction automation in engineering applications.
Oct 10, 2025

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?

Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, current coding benchmarks face limitations such as a lack of exceptionally challenging problems, insufficient test case coverage, and reliance on online platform APIs that limit accessibility. To address these issues, we introduce LiveOIBench, a large-scale competitive programming benchmark featuring 403 expert-curated problems, averaging 60 official test cases each, drawn from 72 contests across 14 Informatics Olympiads held between 2023 and 2025. LiveOIBench has four key features: (1) expert-designed tasks with detailed subtask rubrics and extensive test cases; (2) direct comparison to elite human contestants; (3) continuous updates to reduce contamination risk; and (4) a fully offline, reproducible evaluation system. Benchmarking 34 popular general-purpose and reasoning LLMs, we find that GPT-5 achieves an 81.76th percentile, still falling short of top human contestants, while among the open-weight models, GPT-OSS-120B reaches only the 60th percentile. Reasoning-trace analyses indicate that robust reasoning models prioritize precise problem analysis over excessive exploration. Finally, analyses across release dates, task familiarity, and code similarity find minimal evidence of data contamination in our benchmark. Our leaderboard, code, and data are available at: https://liveoibench.github.io/.
Oct 10, 2025

StatEval: A Comprehensive Benchmark for Large Language Models in Statistics

Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do not reflect the layered, proof-driven nature of real statistical practice. To address this gap, we introduce StatEval, the first large-scale benchmark for statistical reasoning across curricular and research-level settings. StatEval includes over 100,000 curated problems, with 20,000+ foundational questions spanning undergraduate and graduate curricula and 80,000+ research-level proof tasks extracted from leading statistical journals. To construct StatEval, we develop TRACE (Topology and Reasoning-Aware Context Extractor), a multi-agent pipeline with human-in-the-loop validation that converts unstructured academic texts into self-contained theorem-level reasoning tasks. We also propose an Adaptive Process-Based Scoring Pipeline for complex statistical proofs, enabling fine-grained evaluation beyond final-answer matching. Experiments show that while LLMs perform reasonably on foundational tasks, they struggle with rigorous research-level reasoning. Beyond evaluation, StatEval serves as a resource for improving reasoning, as retrieval-augmented generation and domain-specific alignment consistently enhance performance. Together, these results establish StatEval as both a benchmark and an infrastructure for advancing statistical reasoning in LLMs.
Oct 10, 2025

Large Language Model Selection with Limited Annotations

Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotations over fixed evaluation sets. To address this challenge, we develop SELECT-LLM, the first framework for active model selection of LLMs. SELECT-LLM aims to find a small set of queries whose annotations are most informative for identifying the best LLM for a given task. To this end, we introduce a query selection rule based on expected information gain, computed from pairwise similarities between candidate model outputs. Because this rule only uses generated model responses, SELECT-LLM can be applied across candidate models without assumptions about their architecture or access to model weights. This makes it suitable for both open-weight and black-box LLMs. We evaluate SELECT-LLM across 23 datasets, 156 evaluated models, diverse task families, and multiple text evaluation metrics. Across all experiments, SELECT-LLM improves over the strongest baseline in every setting, with annotation cost reductions up to 81.8% for best model selection and up to 84.78% for near-best model selection.
Oct 9, 2025

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

Organic reaction mechanisms describe the step-wise elementary processes by which reactants transform into intermediates and products, and are fundamental to understanding chemical reactivity and guiding molecular and reaction de-sign. While large language models (LLMs) have shown promise on chemical tasks such as synthesis design, it remains unclear to what extent this reflects genuine chemical reasoning capabilities: the ability to generate chemically valid intermediates, maintain consistency across reaction steps, and follow logically coherent multi-step pathways. To investigate this, we introduce oMeBench, the first large-scale, expert-curated benchmark for organic mechanism reasoning, comprising over 10,000 annotated mechanistic steps with reaction type labels, intermediate structures, and difficulty ratings. To enable fine-grained evaluation, we further propose oMeS, a dynamic scoring framework that jointly assesses step-level logical consistency and chemical structural similarity. Systematic evaluation of state-of-the-art LLMs reveals that while current models exhibit promising chemical intuition, they struggle to produce correct and consistent reasoning across multi-step mechanisms. Notably, combining prompting strategies with fine-tuning enables smaller-scale models to achieve performance comparable to closed-source frontier models. We hope oMeBench will serve as a rigorous foundation for advancing AI systems toward genuine chemical reasoning.
Oct 8, 2025

EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models

Socio-economic causal effects depend heavily on their institutional and environmental contexts. The same intervention can produce different, even opposite, effects across regulatory regimes, market conditions, time periods, or populations. This poses a challenge for large language models (LLMs) in decision-support roles: can they infer the direction of a causal effect under a specified context, and revise that judgment when the context changes? To address this, we introduce EconCausal, a large-scale benchmark of 10,490 context-annotated causal triplets extracted from 2,595 high-quality empirical studies in top-tier economics and finance journals, constructed through a rigorous four-stage pipeline with multi-run consensus, context refinement, and multi-critic filtering. Across 19 models, we observe source-sign over-transfer in cross-context prediction. While top models reach ~84% accuracy in single-context prediction, mean accuracy is 74.75% overall but drops to 44.27% when source and target signs disagree. On these cases, accuracy is 11.54 percentage points (pp) lower with the signed source example than with the target input alone. Mean accuracy is below 60% under corrupted source signs. Models also struggle to predict study-reported nonsignificant effects (19.16% accuracy). The dataset and benchmark are publicly available at https://anonymous.4open.science/r/econcausal-benchmark-6F12.
Oct 5, 2025

Psychological Imagination Networks Show Cross-Population Centrality and Clustering Alignment in Humans That Large Language Models Fail to Replicate

Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large language model (LLM) populations remains unknown. We applied psychological network analysis to vividness ratings from two validated questionnaires: the Vividness of Visual Imagery Questionnaire (VVIQ-2) and the Plymouth Sensory Imagery Questionnaire (PSIQ), across geographically and linguistically distinct human samples (Florida, Poland, and London; total N = 2,743) and six large language models (LLMs; Gemma3-12B/27B, their quantization-aware counterparts, Llama3.3-70B, and Llama4-16x17B). Imagination networks were constructed as regularized partial correlation graphs, with node centrality and community structure compared across populations using Pearson correlations and the Adjusted Rand Index (ARI). Human networks showed robust cross-population centrality correlations for expected influence, strength, and closeness (r = 0.31-0.93), and community detection recovered clusters aligned with VVIQ-2 scene contexts (ARI = 0.27-0.40) and PSIQ sensory modalities (ARI = 0.87-1.0). Betweenness centrality was unstable across all populations, consistent with its sensitivity to individual experiential history. LLMs failed to replicate human network structure: LLM-human centrality correlations were weak and largely non-significant after correction, and most LLM configurations produced degenerate single-cluster topologies (median ARI = 0). This failure was consistent across model architectures, parameter scales (12B-272B), and conversational conditions. We posit that these findings may be driven by human imagination networks reflecting memory organization accumulated through embodied experience, a representational structure that linguistic training alone does not reproduce regardless of model scale and conversational memory.
Oct 5, 2025

When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring

Standard language model evaluation assigns scores to single predicted answers, rewarding high-confidence responses regardless of how residual probability mass is distributed over alternative options. This creates a systematic pressure toward overconfident guessing: under accuracy-based schemes, a model maximises its expected score by always committing to an answer rather than abstaining, even when its uncertainty is high. While penalty-based approaches partially address this by raising the confidence threshold for strategic guessing, they still treat all sub-threshold responses identically, ignoring a fundamental distinction in how models can express uncertainty - for example between hedging toward incorrect answers versus hedging toward "I don't know" responses. This paper introduces a novel evaluation metric to solve this problem of not considering a model's entire probability distribution over answer choices. The metric naturally distinguishes between harmful overconfidence in wrong answers and uncertainty expressed through abstention, providing scores in an interpretable default range. Through theoretical analysis and illustrative examples, the metric is shown to offer a more nuanced and aligned evaluation paradigm that incentivises models to express genuine uncertainty rather than guessing. Adapting 12 existing evaluation benchmarks to the metric's variants and measuring performance on six language models shows that for half of the tested benchmarks scores are negative across all tested models, indicating significant tendencies towards hallucination.
Oct 5, 2025

What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models

Large language models (LLMs) are increasingly used as primary knowledge sources, yet their epistemic diversity - defined as the diversity of real-world claims in their outputs - has never been measured. Low epistemic diversity would pose a risk of knowledge collapse as homogeneous LLMs mediate a shrinking in the range of accessible information over time. The dominant paradigm is that overall LLM diversity is low, but this is always with respect to a single point in time, with no reference baseline or consideration for variation across countries. We address this gap in knowledge by performing the first systematic study of epistemic diversity in LLMs across time and cultural context, testing 27 LLMs on 155 topics covering 12 countries, resulting in 1.7M responses and 70M individual claims. We find that epistemic diversity has increased substantially over the past three years, a positive counter to recent diversity pessimism. However, despite progress, we find that every system is less diverse than a search baseline. This gap is not uniform: RAG can improve diversity, while large models are counterintuitively less diverse than smaller ones. Moreover, LLM parametric knowledge systematically reflects English over local-language knowledge for country specific topics. Together, these results demonstrate that while progress on epistemic diversity is tangible, it is insufficient and unevenly distributed.
Oct 1, 2025

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust representations of concepts. The rapid advancement of transformer-based large language models (LLMs) has surfaced a diversity of computational ingredients relevant for model building - architectures, fine-tuning methods, and training datasets among others - yet it remains unclear which are most crucial for developing human-like conceptual representations. Further, most current benchmarks are ill-suited to measuring representational alignment, making LLMs' scores on them unreliable for assessing whether they are progressing as cognitive models. We address these limitations by evaluating over 75 models on a triplet similarity task, a method well established in cognitive science for measuring conceptual representations, using concepts from the THINGS database. We find that instruction fine-tuning and larger attention head dimensionality are among the strongest predictors of human alignment, while activation function choice, multimodal pretraining, and parameter size have limited influence on alignment. Correlations between alignment scores and existing benchmark scores reveal that while some benchmarks (e.g., BigBenchHard) better capture representational alignment than others (e.g., MUSR), none fully accounts for the variance in human-model alignment, demonstrating their insufficiency. Taken together, our findings highlight key computational ingredients for advancing LLMs as models of human conceptual representation and address a key gap in LLM evaluation.
Oct 1, 2025

Rethinking Reward Models for Multi-Domain Test-Time Scaling

The reliability of large language models (LLMs) during test-time scaling is often assessed with external verifiers or reward models that distinguish correct reasoning from flawed logic. Prior work has studied both outcome reward models (ORMs), which assess only the final answer, and process reward models (PRMs), which score intermediate reasoning steps. Although PRMs are often viewed as advantageous due to their finer-grained supervision, much of the supporting evidence comes from math-adjacent settings, and their relative benefits across broader domains remain unclear. We present the first unified evaluation of four reward model variants, discriminative ORM and PRM (dORM, dPRM) and generative ORM and PRM (gORM, gPRM), across 14 diverse domains. Contrary to conventional wisdom, we find that (i) dORM performs on par with dPRM, (ii) gPRM is not competitive, and (iii) overall, gORM is the most robust, yielding significant and consistent gains across every tested domain. We attribute the worse performance of gPRM to the stepwise scoring process, which inherits label noise from LLM-based automatic labeling, leading to difficulties in evaluating long reasoning trajectories, including those involving self-correcting reasoning. Both our theoretical analysis and empirical observations indicate that stepwise aggregation compounds errors as reasoning length increases. These findings challenge the common assumption that fine-grained supervision is always better and support generative outcome verification for multi-domain deployment. Our code is publicly available to facilitate future research in multi-domain settings.
Sep 30, 2025

Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management

Large language models (LLMs) are increasingly used to simulate human behavior in business, economics, and the social sciences, offering a low-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published behavioral-operations experiments, we assess LLM performance along two dimensions: whether LLM-generated data reproduce the original hypothesis-test outcomes, and whether their full response distributions align with human data, measured by Wasserstein distance. We find that LLMs often replicate hypothesis-level effects, suggesting that they can capture salient decision biases and behavioral regularities. However, their response distributions frequently diverge from human data, even for strong proprietary models, with dispersion mismatch playing an important role. We also examine two lightweight mitigation strategies: chain-of-thought prompting and hyperparameter tuning. Both can reduce distributional misalignment, and appropriate tuning can sometimes allow smaller or open-source models to match or outperform larger proprietary systems.
Sep 30, 2025

When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation

As LLMs rapidly saturate existing benchmarks, automated benchmark creation using LLMs (LLM as a benchmark) where a model generates test inputs (LLM as a testset) and evaluates outputs (LLM as an evaluator) has gained traction as a cheap alternative to human curation. We show that this paradigm has a fundamental problem: LLM-generated benchmarks systematically favor the model that created them. Using machine translation as our primary testbed, we find that self bias arises from two compounding sources, LLM as a testset and LLM as an evaluator, and their combination amplifies the effect. Crucially, even when test data is generated with explicit diversity controls, each modelś implicit stylistic tendencies produce homogeneous, model-specific outputs that inflate its own scores. Increasing source text diversity, using our proposed diversity metric, partially mitigates this bias. Self bias is strong enough to cause each model to rank itself first, overriding the peer consensus ordering. We confirm that the phenomenon extends to open-ended generation on the Chatbot Arena task.
Sep 30, 2025

Feedback Forensics: A Toolkit to Measure AI Personality

Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional benchmarks based on automatic checks struggle to measure such traits. Evaluation methods using human feedback such as Chatbot Arena have emerged as a popular alternative. These methods infer "better" personality and other desirable traits implicitly by ranking multiple model responses relative to each other. Recent issues with model releases highlight limitations of these existing opaque evaluation approaches: goblin-obsessed, sycophantic and generally over-the-top personalities have resulted in model rollbacks and extensive media coverage. Despite these known issues, limited public tooling exists to explicitly evaluate model personality. We introduce Feedback Forensics: an open-source toolkit to track AI personality and related behavioural traits, both those encouraged by human (or AI) feedback, and those exhibited across AI models trained and evaluated on such feedback. Feedback Forensics is adaptive and can automatically find new traits appearing in models. We demonstrate the toolkit's usefulness in two steps: (A) first we analyse the personality traits encouraged in popular human feedback datasets including MultiPref, PRISM and data from Chatbot Arena; and (B) then use our toolkit to analyse how much popular models exhibit such traits. We release (1) our Feedback Forensics toolkit alongside (2) a web app tracking AI personality in popular models and feedback datasets and (3) the underlying annotation data, see https://github.com/rdnfn/feedback-forensics.
Sep 30, 2025

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowledge. However, existing benchmarks are limited, as they focus solely on final-answer questions or high-school competition problems. To address this gap, we introduce IMProofBench, a private benchmark consisting of 77 peer-reviewed problems developed by expert mathematicians. Each problem requires a detailed proof and is paired with subproblems that have final answers, supporting both an evaluation by human experts and a large-scale quantitative analysis through automated grading. Furthermore, unlike prior benchmarks, the evaluation setup simulates a realistic research environment: models operate in an agentic framework with tools like web search for literature review and mathematical software such as SageMath. Our results show that current LLMs can already solve a significant percentage of research-level questions. IMProofBench will continue to evolve as a dynamic benchmark in collaboration with the mathematical community, ensuring its relevance for evaluating the next generation of LLMs.
Sep 25, 2025

Evidence for Limited Metacognition in LLMs

The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce a novel methodology for quantitatively evaluating metacognitive abilities in LLMs. Taking inspiration from research on metacognition in nonhuman animals, our approach eschews model self-reports and instead tests to what degree models can strategically deploy knowledge of internal states. Using two experimental paradigms, we demonstrate that frontier LLMs introduced since early 2024 show increasingly strong evidence of certain metacognitive abilities, specifically the ability to assess and utilize their own confidence in their ability to answer factual and reasoning questions correctly and the ability to anticipate what answers they would give and utilize that information appropriately. We buttress these behavioral findings with an analysis of the token probabilities returned by the models, which suggests the presence of an upstream internal signal that could provide the basis for metacognition. We further find that these abilities 1) are limited in resolution, 2) emerge in context-dependent manners, and 3) seem to be qualitatively different from those of humans. We also report intriguing differences across models of similar capabilities, suggesting that LLM post-training may have a role in developing metacognitive abilities.
Sep 25, 2025

Measuring Combinatorial Creativity in Large Language Models and Humans

Combinatorial creativity, the process of combining familiar ideas in unfamiliar ways, is one of the foremost engines of scientific, technological, and artistic progress. This work introduces Kombine, an LLM benchmark for combinatorial creativity tasking models to discover surprising, original, and useful associations, analogies, and blends between unrelated entities, and to use those analogies and blends to invent novel concepts by re-combining the parts of existing ones. In a large-scale study across 35 LLMs, we find that: (1) LLMs are 10-16 percentage points better at discovering associations and analogies than blends, and (2) exhibit an abstraction bottleneck on blending, in which even frontier LLMs struggle to find a shared abstraction between inputs and instantiate a coherent blended space. (3) LLMs also exhibit inventive homogeneity, in which one in five concepts invented for a given item reuses properties invented by another model. Moreover, (4) models are 14×14\times more likely to reuse other invented properties on blends than analogies, and (5) models from the same provider are 2.3×2.3\times more likely to reuse properties than those from different providers. Next, in a comparative study involving 75 humans on the same tasks, we find that (6) humans score below nearly every LLM on each task and (7) both humans and LLMs find blending most difficult, but association is easier than analogy for LLMs, while analogy is easier than association for humans. Lastly, (8) humans and LLMs access distinct regions of semantic space on each task, suggesting that combinatorial creativity could benefit from systematic human-AI collaboration to enhance conceptual diversity. In summary, we provide a framework to assess progress towards LLMs, AI systems, and human-AI collaborations more broadly, that can elicit combinatorial creativity in a setting relevant to scientific and technological innovation.
Sep 25, 2025

Predicting LLM Reasoning Performance with Small Proxy Model

Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up. However, this approach becomes challenging for reasoning capabilities, which exhibit emergent behavior that only appear reliably at larger model sizes, often exceeding 7B parameters. To address this, we introduce rBridge, showing that small proxies (≤\leq1B) can effectively predict large-model reasoning by aligning more closely with (1) the pre-training objective and (2) the target task. rBridge achieves this by weighting negative log-likelihood with task alignment, using reasoning traces from frontier models as gold labels. In our experiments, rBridge (i) reduces dataset ranking costs by over 100x relative to the best baseline, (ii) achieves the strongest correlation across six reasoning benchmarks at 1B to 32B scale, and (iii) zero-shot transfers predictive relationships across pre-training datasets at 1B to 7B scale. These findings indicate that rBridge offers a practical path for exploring reasoning-oriented pre-training at lower cost.
Sep 25, 2025

Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions

Modern ML research increasingly faces an evaluation bottleneck: building benchmarks and running experiments is costly, slowing iteration. We ask how much can be inferred about evaluation outcomes before experiments, given only a natural-language description of the task and setup. We call this setting anticipatory evaluation. We introduce EVALCAST, a literature-grounded resource of 2,290 description-performance pairs from 1,519 arXiv papers, including a test set of papers published after the model's knowledge cutoff. We evaluate two tasks: predicting absolute performance through regression and comparing benchmark difficulty through pairwise prediction. Experiments with frontier LLMs show that accurate regression remains challenging, while pairwise predictions can recover relative performance ordering under matched settings. Comparable performance on post-cutoff and streaming evaluations suggests that the observed signal is not solely attributable to previously reported results. Overall, EVALCAST provides a resource and evaluation framework for studying anticipatory evaluation and its potential use in prioritizing benchmarks.
Sep 24, 2025

Polarity Detection of Sustainable Development Goals in News Text

The United Nations' Sustainable Development Goals (SDGs) provide a globally recognised framework for addressing major societal, environmental, and economic challenges. While recent advances in natural language processing (NLP) and large language models (LLMs) have enabled the automatic identification of SDG-related content, they do not capture whether the described events represent progress toward or regression from a specific goal. To address this gap, we introduce the novel task of SDG polarity detection and present SDG-POD, a benchmark dataset combining manually annotated and synthetically generated examples. We evaluate six state-of-the-art open-source LLMs under both zero-shot and fine-tuning settings and investigate the impact of synthetic data augmentation on model performance. Our results show that SDG polarity detection remains challenging for current LLMs; however, fine-tuned models, particularly QWQ-32B, achieve the best overall performance, with especially strong results on SDG-9, SDG-12, and SDG-15. Furthermore, we demonstrate that synthetic training data consistently improves model robustness and classification performance. This work introduces a new benchmark for SDG polarity detection and provides practical insights into developing LLM-based systems for sustainability monitoring.
Sep 22, 2025

The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies

Large language models (LLMs) are increasingly used to simulate human collective behavior, yet claims that such simulations are human-like remain largely untested. We conducted a systematic audit (pre-registered on OSF) of LLM-based social simulations across four databases (Scopus, IEEE Xplore, ACM Digital Library, and arXiv). Across 576 studies reported in 350 recent papers, we applied six methodological evaluations: agent Profile, Interaction, Memory, Minimal-Control, Unawareness, and Realism (PIMMUR). Coding every study against pre-specified rules, we revealed that PIM were met more often than MUR. Frontier LLMs correctly identified the underlying social experiment in 65.2% of cases, and 50.6% of prompts imposed constraints that pre-determined the outcome. These compliance rates are upper bounds, because incomplete methodological reporting (for example, unreleased prompts) limits the available evidence. Reproducing five representative experiments (e.g., opinion dynamics), we found that reported collective phenomena often vanish or reverse once PIMMUR principles are enforced, indicating that many "emergent" behaviors are methodological artifacts rather than genuine social dynamics. Current LLM simulations may therefore capture model-specific biases rather than universal features of human social behavior, raising concerns about their use as scientific proxies for human society.
Sep 22, 2025

Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs

Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program analysis and generation. Yet testing them on specific tasks remains difficult and costly: many prompts lack ground truths, forcing reliance on human judgments, while existing test adequacy measures typically rely on output uncertainty and thus are only available after full inference. A key challenge is to assess how useful a test input is in a way that reflects the demands of the task, ideally before even generating any output. We introduce Clotho, a task-specific, pre-generation test adequacy measure that estimates input difficulty directly from LLM hidden states. Given a large pool of unlabelled inputs for a specific task, Clotho uses a Gaussian Mixture Model (GMM) to adaptively sample the most informative cases for human labelling. Based on this reference set the GMM can then rank unseen inputs by their likelihood of failure. In our empirical evaluation across eight benchmark tasks and three open-weight LLMs, Clotho can predict failures with a ROC-AUC of 0.716, after labelling reference sets that are on average only 5.4% of inputs. It does so without generating any outputs, thereby significantly reducing LLM execution costs compared to output-based uncertainty or confidence measures. Comparison of Clotho and these post-generation adequacy measures shows that the two approaches complement each other. Crucially, we show that adequacy scores learnt from open-weight LLMs transfer effectively to proprietary models, extending the applicability of the approach. When prioritising test inputs for proprietary models, Clotho increases the average number of failing inputs from 18.7 to 42.5 out of 100, compared to random prioritisation.