LLM Evaluation

Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding. Furthermore, the rapid proliferation of LLMs has created the implicit assumption that more sophisticated prompting techniques yield better performance. Several studies claim such gains, but report them under differing models, prompt wordings and answer-extraction rules, so the gains cannot be attributed to the technique alone. We address this gap with ReasonLab, an evaluation framework in which the prompting technique is a first-class experimental variable alongside the model and the dataset, and which retains every generation for inspection. Using ReasonLab we conduct a controlled study of 8 prompting techniques across 10 MCQA datasets, 27 model configurations and 480,927 evaluations at temperature 0. We find that the prompting technique is a minor determinant of accuracy: on configurations without a reasoning budget the reasoning triggers improve on direct prompting by only 3.92 to 4.69 pp and are indistinguishable from one another, and on configurations with reasoning enabled no technique differs by more than 0.51 pp. Self-Generate is the only technique with a consistent effect, a reduction of 2.95 pp. We further investigate three phenomena: (1) the comparison of models on a common set of datasets, where model size does not predict accuracy, (2) the trade-offs across thinking budgets, where enabling reasoning is worth up to 12.74 pp whereas an eightfold budget increase adds only 0.48 to 2.10 pp, and (3) the variation in dataset difficulty, with 60% of benchmarks below 70% accuracy and a 43.9 pp spread from easiest to hardest. These results suggest that, for MCQA, the prompting technique is a minor lever compared with enabling model reasoning, and that substantial headroom remains.

Annotation automation via Large Language Models (LLMs) is the core approach for scaling NLP datasets; however, LLM behavior with respect to closed-set instructions in low-resource languages has not been well studied. We present MultiSoc-4D, a Bengali social media dataset benchmark, which contains 58K+ social media comments from six sources annotated along four dimensions: category, sentiment, hate speech, and sarcasm. By employing a structured pipeline where ChatGPT, Gemini, Claude, and Grok individually annotate separate partitions, while sharing a common validation set of 20%, we diagnose LLM behavior systematically. We discover a prevalent phenomenon called "instruction-induced label collapse", wherein LLMs show a systematic preference towards fallback labels (Other, Neutral, No), leading to high agreement rates but under-detection of minority categories. For example, we find that LLMs failed to detect 79% and 75% of instances with hateful and sarcastic content compared to a human-calibrated reference. Furthermore, we prove that it represents a "label agreement illusion", statistically validated via almost null Fleiss' Kappa ($κ\approx -0.001$) on sarcasm detection. Across 40+ LLMs, we benchmark this annotation bias propagation within the training pipeline, regardless of architectural differences. We release MultiSoc-4D as a diagnostic benchmark for annotation biases in Bengali NLP.

LLM-as-a-Judge evaluation has become a standard tool for assessing base model performance. However, characterizing performance via the naive estimator, i.e., raw judge outputs, is systematically biased. Recent work has proposed estimators to correct this bias, but their reliability depends critically on judge quality and, for model comparisons, on calibration stability. Sharing calibration across compared models is practically attractive but can introduce severe bias, including cases where the comparison estimate points in the wrong direction with high apparent confidence. We study these failure modes through analytical results, simulations over judge quality ($J$) and cross-model calibration instability ($ΔJ$), and a real-data MMLU-Pro case study with sign reversal. We propose $J$ and $ΔJ$ as diagnostics for when corrected estimates, especially shared-calibration comparisons, are likely unreliable, and provide reporting guidance for LaaJ evaluation.

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a limitation with real consequences in high-stakes domains like medicine and finance. We evaluate eight LLMs on their context-certainty obedience, measuring how well they adjust responses to match expressed context certainty. Our analysis reveals systematic limitations: LLMs struggle to recall prior knowledge after observing an uncertain context, misinterpret expressed certainties, and overtrust complex contexts. To address these, we propose an interaction strategy combining prior reminders, certainty recalibration, and context simplification. This approach reduces obedience errors by 25% on average, without modifying model weights, demonstrating the efficacy of interaction design in enhancing LLM reliability. Our contributions include a principled evaluation metric, empirical insights into LLMs' uncertainty handling, and a portable strategy to improve context-certainty obedience across diverse LLMs.

Large Language Models (LLMs) have achieved great improvements in recent years. Nevertheless, it still remains unclear how good LLMs are for reasoning tasks, especially for long-chain ones. In this paper, we evaluate LLMs' performance on the simplest yet long-chain reasoning task, namely the Equivalence Class Problem (ECP), i.e., determining whether two variables are equal given a set of randomly generated equivalence relations. We consider both reasoning and non-reasoning representative LLMs over a large variety of problem instances, ranging over different numbers of variables, connectivity probabilities, prompts, and other factors. The experimental results show that non-reasoning LLMs fail ECP, while reasoning models are significantly better but still struggle to completely solve this problem. Interestingly, considering various connectivity probabilities with a fixed number of variables, we observe that, for non-reasoning models, the hardest problem instances coincide with the phase transition point of ln n/(n-1), suggesting the chaos of the problem; in contrast, for reasoning models, the hardest ones coincide with the biggest diameter, suggesting the reasoning difficulty of the problem.

Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries. Despite their prevalence, researchers and practitioners lack methods and empirical insights to make informed decisions about when and what types of human-like behaviors LLMs should exhibit. To fill this gap, we present a multi-dimensional analysis of the prevalence, potential effects, and controllability of these behaviors using LLM-as-a-judge and human evaluation. Across 21,000 multi-turn conversations from four widely used models (gpt-4o, gpt-4.1-mini, claude-sonnet-4.6, gemini-2.5-flash), we find that human-like behaviors are pervasive but vary across models and user factors (conversation goals and user profiles). In terms of perceived appropriateness, human evaluators judged self-referential and relationship-building behaviors as less appropriate from LLMs than from humans, but boundary-maintaining behaviors more appropriate from LLMs than from humans. Finally, we show that system prompting can control these behaviors, though it requires careful evaluation to avoid unintended effects. We discuss the implications of our findings and provide recommendations for responsible LLM design and evaluation.

Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assistants. This paper introduces IntentGrasp, a comprehensive benchmark for evaluating the intent understanding capability of LLMs. Derived from 49 high-quality, open-licensed corpora spanning 12 diverse domains, IntentGrasp is constructed through source datasets curation, intent label contextualization, and task format unification. IntentGrasp contains a large-scale training set of 262,759 instances and two evaluation sets: an All Set of 12,909 test cases and a more balanced and challenging Gem Set of 470 cases. Extensive evaluations on 20 LLMs across 7 families (including frontier models such as GPT-5.4, Gemini-3.1-Pro, and Claude-Opus-4.7) demonstrate unsatisfactory performance, with scores below 60% on All Set and below 25% on Gem set. Notably, 17 out of 20 tested models perform worse than a random-guess baseline (15.2%) on Gem Set, while the estimated human performance is ~81.1%, showing substantial room for improvement. To enhance such ability, this paper proposes Intentional Fine-Tuning (IFT), which fine-tunes the models on the training set in IntentGrasp, yielding significant gains of 30+ F1 points on All Set and 20+ points on Gem Set. Tellingly, the leave-one-domain-out (Lodo) experiments further demonstrate the strong cross-domain generalizability of IFT, verifying that it is a promising approach to substantially enhancing the intent understanding of LLMs. Overall, by benchmarking and boosting intent understanding ability, this study sheds light on a promising path towards more intentional, capable, and safe AI assistants for human benefits and social good.

Ranking LLMs via pairwise human feedback underpins current leaderboards for open-ended tasks, such as creative writing and problem-solving. We analyze ~89K comparisons in 116 languages from 52 LLMs from Arena, and show that the best-fit global Bradley-Terry (BT) ranking is misleading. Nearly 2/3 of the decisive votes cancel out, and even the top 50 models according to the global BT ranking are statistically indistinguishable (pairwise win probabilities are at most 0.53 within the top 50 models). We trace this failure to strong, structured heterogeneity of opinions across language, task, and time. Moreover, we find an important characteristic - language plays a key role. Grouping by language (and families) increases the agreement of votes massively, resulting in two orders of magnitude higher spread in the ELO scores (i.e., very consistent rankings). What appears as global noise is in fact a mixture of coherent but conflicting subpopulations. To address such heterogeneity in supervised machine learning, we introduce the framework of $(λ, ν)$-portfolios, which are small sets of models that achieve a prediction error at most $λ$, "covering" at least a $ν$ fraction of users. We formulate this as a variant of the set cover problem and provide guarantees using the VC dimension of the underlying set system. On the Arena data, our algorithms recover just 5 distinct BT rankings that cover over 96% of votes at a modest $λ$, compared to the 21% coverage by the global ranking. We also provide a portfolio of 6 LLMs that cover twice as many votes as the top-6 LLMs from a global ranking. We further construct portfolios for a classification problem on the COMPAS dataset using an ensemble of fairness-regularized classification models and show that these portfolios can be used to detect blind spots in the data, which might be of independent interest to policymakers.

Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify the contract under which a scenario-based audit can be interpreted as deployment evidence. Scores are valid only under a fixed scenario pack, rubric, auditor, judge, sampling configuration, and rerun budget. Because no labels are available, we replace ground-truth agreement with an instrumental-validity chain: responsiveness to a controlled safe-versus-abliterated contrast, dominance of target-driven variance over auditor and judge artifacts, and stability across reruns. We instantiate the chain in SimpleAudit, a local-first scoring instrument, and validate it on a Norwegian safety pack. Safe and abliterated targets separate with AUROC values between 0.89 and 1.00, target identity is the dominant variance component ($η^2 \approx 0.52$), and severity profiles stabilize by ten reruns. Applying the same chain to Petri shows that it admits both tools. The substantial differences arise upstream of the chain, in claim-contract enforcement and deployment fit. A Norwegian public-sector procurement case comparing Borealis and Gemma 3 demonstrates the resulting evidence in practice: the safer model depends on scenario category and risk measure. Consequently, scores, matched deltas, critical rates, uncertainty, and the auditor and judge used must be reported together rather than collapsed into a single ranking.

Large language models (LLMs) power deep research agents that synthesize information from hundreds of web sources into cited reports, yet these citations cannot be reliably verified. Current approaches either trust models to self-cite accurately, risking bias, or employ retrieval-augmented generation (RAG) that does not validate source accessibility, relevance, or factual consistency. We introduce the first source attribution evaluation framework that uses a reproducible AST parser to extract and evaluate inline citations from LLM-generated Markdown reports at scale. Unlike methods that verify claims in isolation, our framework closes the loop by retrieving the actual cited content, enabling human or model evaluators to judge each citation against its source. Citations are evaluated along three dimensions. (1) Link Works verifies URL accessibility, (2) Relevant Content measures topical alignment, and (3) Fact Check validates factual accuracy against source content. We benchmark 14 closed-source and open-source LLMs across three evaluation dimensions using rubric-based LLM-as-a-judge evaluators calibrated through human review. Our results reveal that even the strongest frontier models maintain link validity above 94% and relevance above 80%, yet achieve only 39-77% factual accuracy, while fewer than half of open-source models successfully generate cited reports in a one-shot setting. Ablation studies on research depth show that Fact Check accuracy drops by approximately 42% on average across two frontier models as tool calls scale from 2 to 150, demonstrating that more retrieval does not produce more accurate citations. These findings reveal a critical disconnect between surface-level citation quality and factual reliability, and our framework provides the evaluation infrastructure to assess the disconnect.

Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.g., jailbreaks or successful task completion by an agent -- often emerge only after repeated interactions. These events might be rare, and under any feasible computational budget, remain unobserved. Recent conformal survival frameworks construct reliable lower predictive bounds (LPBs) on the number of iterations to trigger the event of interest, but rely on static budget allocation that is inefficient in multi-turn setups. To address this, we introduce \emph{Dynamic Allocation via PRojected Optimization} (DAPRO), the first theoretically valid dynamic budget allocation framework for bounding the time-to-event in multi-turn LLM interactions. We prove that DAPRO satisfies the budget constraint and provides distribution-free, finite-sample coverage guarantees without requiring the conditional independence between censoring and event times assumed by prior conformal survival approaches. A key theoretical contribution is a novel coverage bound that scales with the square root of the mean censoring weight rather than the worst-case weight, yielding provably tighter guarantees than prior work. Furthermore, DAPRO can be employed to obtain unbiased, low-variance estimates of population-level evaluation metrics, such as the jailbreak rate, under limited computing resources. Comprehensive experiments across agentic task success, adversarial jailbreaks, toxic content generation, and RAG hallucinations using LLMs such as Llama 3.1 and Qwen 2.5 demonstrate that DAPRO consistently achieves coverage closer to the nominal level with lower variance than static baselines, while satisfying the budget constraint.

Creative AI systems are typically evaluated at the level of individual utility, yet creative outputs are consumed in populations: an idea loses value when many others produce similar ones. This creates an evaluation blind spot, as AI can improve individual outputs while increasing population-level crowding. We introduce a human-relative framework for benchmarking AI-induced human diversity collapse without requiring human-AI interaction data, providing an ex ante protocol to estimate crowding risk from model-only generations and matched unaided human baselines. By modeling ideas as congestible resources, we show that source-level crowding is identifiable from within-distribution comparisons, yielding an excess-crowding coefficient $Δ$ and a human-relative diversity ratio $ρ$. We show that $ρ\ge1$ is the no-excess-crowding parity condition and connect $Δ$ to an adoption game with exposure-dependent redundancy costs. Across short stories, marketing slogans, and alternative-uses tasks, three frontier LLMs fall below parity across crowding kernels. Estimates stabilize with feasible model-only sample sizes. Importantly, generation-protocol variants show that crowding can be reduced through targeted design, making diversity collapse an actionable, development-time evaluation target for population-aware creative AI.

In this work, we conduct an analysis to examine the consistency of Large Language Models (LLMs) with respect to their own generated responses in an emotionally-driven conversational context. Specifically, the text generated by LLM is framed as a query to the same model, and its responses are subsequently assessed. This is performed with three queries across two dimensions of extreme and moderate emotions. The three queries are, in particular, false claim queries that contain inherently wrong assumptions (false presuppositions) in increasing order of intensity. Two commercial models, Claude-3.5-haiku, GPT4o-mini, and a medium-sized model, Mistral-7B, are considered in the study. Our findings indicate that LLMs exhibit below-average performance and remain vulnerable to false beliefs embedded within queries. This susceptibility is especially pronounced for moderate emotional content. Furthermore, an extended attention-score-based analysis highlights a shift in models' priority from evaluative to generative. The results raise important considerations for LLMs' deployment in high-stakes, emotionally sensitive contexts.

While many studies of Large Language Model (LLM) reasoning capabilities emphasize mathematical or technical tasks, few address reasoning about social concepts: the abstract ideas shaping social norms, culture, and institutions. This understudied capability is essential for modern models acting as social agents, yet no systematic evaluation methodology targets it. We introduce SCRuB (Social Concept Reasoning under Rubric-Based Evaluation), a framework designed for this setting of task indeterminacy. Our goal is to measure the degree to which a model reasons about social concepts with the depth and critical rigor of a human expert. SCRuB proceeds in three phases: prompt construction from established sources, response generation by experts and models, and comparative evaluation using a five-dimensional critical thinking rubric. To enable generalization of the pipeline, we introduce a Panel of Disciplinary Perspectives ensemble validated against independent expert judges. We release SCRuBEval (n=4,711 evaluation prompts) and SCRuBAnnotations (300 expert-authored responses and 150 expert comparative judgments from 45 PhD-level scholars). Our results show that frontier models consistently outperform human experts across all five rubric dimensions. Across 1,170 pairwise comparisons, expert judges ranked a model response first in 80.8% of judgments and preferred model responses overall 74.4% of the time. Ultimately, this study provides the first expert-grounded demonstration of evaluation saturation for social concept reasoning: the single-turn exam-style format has reached its ceiling for models and humans alike.

Vacuity, or Uncertainty Mass (UM), is commonly used as a metric to evaluate Out-of-Distribution (OOD) detection in Evidential Deep Learning (EDL). It generally involves dividing the number of classes ($K$) by the total strength of belief ($S$) of the model's predictions, where $S$ is derived from summing the Dirichlet parameters. As such, UM is sensitive to the cardinality of $K$. In particular, it is unlikely in practice that there is a linear relationship between $K$ and $S$ as $K$ and $S$ increase due to the nature of EDL (suppressing incorrectly assigned evidence). As a result, when comparing In Distribution (ID) and OOD results, it is important that $K_{\mathrm{ID}}$ and $K_{\mathrm{OOD}}$ are equal; something that is not always ensured in practice. We provide an empirical demonstration of how results for AUROC and AUPR can substantially differ when class cardinality between ID and OOD differs by 1, with AUROC differing by as much as 0.318 and AUPR by 0.613 for standard EDL, and AUROC by 0.360 and AUPR by 0.683 for IB-EDL. More concretely, our findings isolate an evaluation artefact: when K differs between ID and OOD, AUROC/AUPR can be artificially inflated without any change in model predictions. We further discuss the evaluation of EDL over causal language models using Multiple-Choice Question-Answer (MCQA) datasets and argue for clearer definitions of ID and OOD in this context. Our primary contribution is an empirical and theoretical demonstration that vacuity-based OOD detection in EDL-fine-tuned LLMs is highly sensitive to uncontrolled differences in evaluated class cardinality.

Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context divergence as an observable within-item change in behavior induced by framing a fixed task as an evaluation, a live deployment interaction, or a neutral request, and present a paired-prompt protocol that measures it in open-weight LLMs while controlling for paraphrase variation, benchmark familiarity, and judge framing-sensitivity. Across five instruction-tuned checkpoints from four open-weight families plus a matched OLMo-3 base/instruct ablation ($20$ paired items, $840$ generations per checkpoint), we find striking heterogeneity. OLMo-3-Instruct alone is eval-cautious -- evaluation framing raises refusal vs. neutral by $11.8$pp ($p=0.007$) and reduces harmful compliance vs. deployment by $3.6$pp ($p=0.024$, $0/20$ items inverted) -- while Mistral-Small-3.2, Phi-3.5-mini, and Llama-3.1-8B are deployment-cautious}, with marginal eval-vs-deployment refusal effects of $-9$ to $-20$pp. The matched OLMo-3 base also exhibits the deployment-cautious pattern, identifying alignment as the inversion stage; within Llama-3.1, the $70$B model preserves direction with attenuated magnitude, ruling out a simple ``small-model effect that reverses at scale.'' One caveat: the cross-family heterogeneity is judge-dependent. Re-judging with a different-family safety classifier (Llama-Guard-3-8B) preserves the within-OLMo eval-cautious direction but flattens the cross-family contrast, indicating that the two judges operationalize distinct constructs.

Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies at the boundary, where the per-prompt pass probability is near $0.5$ under random-sampling decoding strategy, and propose Dynamic Boundary Evaluation (DBE), which actively locates each model's boundary and places it on a globally comparable difficulty scale. DBE delivers three artifacts: (i) a calibrated item bank covering safety, capability, and truthfulness, with per-item difficulty labels validated across $9$ reference LLMs; (ii) Skill-Guided Boundary Search (SGBS), a search algorithm that finds boundary items for a given target LLM using only API-level query access; and (iii) an evaluation protocol that places a new LLM on a unified ability scale and grows the evaluation set adaptively when the target falls outside the bank's coverage. We instantiate DBE on four categories spanning safety (harmful request refusal, over-refusal), capability (constrained instruction following), and truthfulness (multi-turn sycophancy resistance). The resulting evaluation covers a broader model spectrum without saturation while remaining compatible with existing datasets.

We introduce an evaluation framework of 500 C verification tasks across five property types (memory safety, overflow, termination, reachability, data races) built on SV-COMP 2025, and evaluate 14 models across six families. We find that high overall accuracy masks a critical weakness: while most models reliably confirm properties hold, violation detection varies widely and degrades sharply with program length. To close this gap, we train on formal verification artifacts: running the Soteria symbolic execution engine on generic open-source C code and using the resulting traces for continued pretraining of Qwen3-8B. Just ${\sim}$3,000 bug traces combined with chain-of-thought reasoning at inference time improve violation detection by over 17 percentage points, producing one of the most balanced accuracy profiles among evaluated models. On violation detection, the trained 8B model outperforms the 4$\times$ larger Qwen3-32B without thinking and approaches it in overall accuracy. The interaction between trace training and chain-of-thought is superadditive: neither alone provides meaningful gains, but their combination does. Improvements transfer across all five property types, including ones the training traces do not target. Our 28 configurations confirm the gains stem from trace semantics, not code volume, and that trace curation and format matter.

Large language model (LLM) outputs arise from complex interactions among prompts, system instructions, model parameters, and architecture. We refer to specific configurations of these factors as generation conditions, each of which can bias outputs in various ways. Understanding how different generation conditions shape model behaviors is essential for tasks such as prompt design and model evaluation, yet it remains challenging due to the stochastic and open-ended nature of text generation. We present an approach to visually compare LLM outputs across generation conditions by modeling responses as collections of linguistic choices, including content, expression, and structure. We extract these choices using natural language processing pipelines and represent their distributions across repeated samples. We then visualize these distributions as visual fingerprints, enabling direct, distribution-level comparison of condition-specific tendencies. Through four usage scenarios, we demonstrate how visual fingerprints reveal consistent patterns in LLM behavior that are difficult to observe through individual responses or aggregate metrics.

This study contributes to a growing line of research in comparing LLM-generated texts with human-authored text, in this case, English news text. We focus in particular on the evaluation of syntactic properties through formal grammar frameworks. Our analysis compares two generations of LLMs in the context of two human-authored English news datasets from two different years. Employing the Head-Driven Phrase Structure Grammar (HPSG) formalism, we investigate the distributions of syntactic structures and lexical types of AI-generated texts and contrast them with the corresponding distributions in the human-authored New York Times (NYT) articles. We use diversity metrics from ecology and information theory to quantify variation in grammatical constructions and lexical types. We show that English news text has changed little in the given time frame, while newer LLMs display reduced syntactic and, especially, lexical diversity compared to older, non-instruction-tuned models. These findings point to future work in studying effects of instruction tuning, which, while enhancing coherence and adherence to prompts, may narrow the expressive range of model output.

Large Language Models (LLMs) are evolving into autonomous trading agents, yet existing benchmarks often overlook the interplay between architectural reasoning and strategy consistency. We propose Strat-LLM, a framework grounded in Stratified Strategy Alignment. Operating in a live-forward setting throughout 2025, it integrates heterogeneous data including sequential prices, real-time news, and annual reports to eliminate look-ahead bias. Extensive stress tests on A-share and U.S. markets reveal: (1) reasoning-heavy models achieve peak utility in Free Mode via internal logic, whereas standard models require Strict Mode as a vital risk anchor; (2) alignment utility is regime-dependent, with Free and Guided modes capturing momentum in uptrending markets, while Strict Mode mitigates drawdowns in downtrends; (3) mid-scale models (35B) show optimal fidelity under strict constraints, whereas ultra-large models (122B) suffer an alignment tax under rigid rules but gain a performance premium in Guided Mode; (4) standard LLMs often fall into a high win-rate trap, optimizing for small gains at the expense of total returns, which can only be mitigated through deep reasoning or strict external guardrails. Project details are available at https://Strat-LLM.github.io.

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We study inference for this procedure-level target under explicit tuning budgets. We propose SIREN, a selection-aware repeated-split reporting protocol that freezes the post-search shortlist, separates splitwise selection from held-out evaluation, and uses an item-level Gaussian multiplier bootstrap for uncertainty quantification. In a fixed-shortlist regime with smooth stabilized selection, the estimator admits a first-order item-level representation, and the bootstrap yields valid simultaneous inference on a finite budget grid. This supports confidence intervals for procedure-performance curves and pre-specified equal-budget and cross-budget comparisons. Controlled simulations and MMLU-Pro tuning experiments show that winner-based reporting can be optimistic and can change deployment conclusions, while SIREN remains close to the finite-sample reporting target.

Verifiers are crucial components for enhancing modern LLMs' reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and faceslimitations in data diversity. In this paper, wepropose LOVER, an unsupervised verifier regularized by logical rules. LOVER treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints on multiple reasoning paths:negation consistency, intra-group consistency,and inter-group consistency (grouped by thefinal answer). By incorporating logical rulesas priors, LOVER can leverage unlabeled examples and is directly compatible with any offthe-shelf LLMs. Experiments on 10 datasetsdemonstrate that LOVER significantly outperforms unsupervised baselines, achieving performance comparable to the supervised verifier(reaching its 95% level on average). The sourcecode is publicly available at https://github.com/wangxinyufighting/llm-lover.

Large language models often improve reasoning by sampling multiple outputs and aggregating their final answers, but precise and efficient control of error levels remains a challenging task. In particular, deciding when to stop sampling remains difficult when the stopping rule is data-dependent and the set of possible answers is not known in advance. We study anytime-valid certification of a prespecified target answer as the unique mode of the model's response distribution, a guarantee distinct from answer correctness. We propose the Certification by Intersection-union Testing with E-processes (CITE) algorithm, which provably controls false certification at any prescribed level under arbitrary data-driven stopping, without requiring prior knowledge of the answer category set. We also prove an category-set-size-free stopping-time rate, establish matching minimax lower bounds up to constants in the main regime, and extend the construction to confidence-weighted voting. Simulations and LLM self-consistency experiments show empirical error control and improved certification in diffuse-tail settings.

We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks. Existing evaluations conflate representation quality with model capacity. Therefore, failures cannot be attributed to the representation rather than to the model that processes it. We formalize four functional axioms (Causality, Minimality, Separability, and Stability) and define a quantitative measure for each, computed directly on the representation independently of downstream accuracy. We audit open-weight LLMs across 23 reasoning tasks (e.g., Spatial Reasoning, Factual QA). We find that no candidate satisfies all four axioms simultaneously, that the representations distinguish task type reliably but cannot distinguish between two questions within the same task, and that the representations encode little information beyond what is already present in the input embedding. The failure is consistent across dense, reasoning-distilled, and RL-trained model families, indicating that the gap is structural rather than a property of model size or training procedure.

Large Language Models (LLMs) perform strongly on many language tasks, but their capability in structurally constrained, accessibility-critical modalities such as Braille remains unclear. We evaluate state-of-the-art LLMs on bidirectional Korean-Braille translation using a human-annotated dataset. Despite expectations that multilingual, instruction-tuned models can generalize to Braille via text representations, we find consistently poor, unstable outputs and substantial disagreement with human judgments. These results point to missing Braille-aware tokenization and weak alignment between Korean and Braille patterns. In contrast, supervised fine-tuning of a small model (T5-small) on the same data yields large and stable gains over zero-shot and prompted LLM baselines across standard metrics (SacreBLEU, ChrF++, CER, BLEU, ROUGE-L, METEOR, CIDEr). Our findings reveal a systematic limitation of current LLMs and demonstrate the effectiveness of modest task-specific supervision.

Background: Existing MRI LLM benchmarks rely mainly on review-book multiple-choice questions, where top proprietary models already score highly, limiting discrimination. No systematic benchmark has evaluated vendor-specific scanner operational knowledge central to research MRI practice. Purpose: We developed MRI-Eval, a tiered benchmark for relative model comparison on MRI physics and GE scanner operations knowledge using primary multiple-choice questions (MCQ), with stem-only and primed diagnostic conditions as complementary analyses. Methods: MRI-Eval includes 1365 scored items across nine categories and three difficulty tiers from textbooks, GE scanner manuals, programming course materials, and expert-generated questions. Five model families were evaluated (GPT-5.4, Claude Opus 4.6, Claude Sonnet 4.6, Gemini 2.5 Pro, Llama 3.3 70B). MCQ was primary; stem-only removed options and used an independent LLM judge; primed stem-only tested responses to incorrect user claims. Results: Overall MCQ accuracy was 93.2% to 97.1%. GE scanner operations was the lowest category for every model (88.2% to 94.6%). In stem-only, frontier-model accuracy fell to 58.4% to 61.1%, and Llama 3.3 70B fell to 37.1%; GE scanner operations stem-only accuracy was 13.8% to 29.8%. Conclusion: High MCQ performance can mask weak free-text recall, especially for vendor-specific operational knowledge. MRI-Eval is most informative as a relative comparison benchmark rather than an absolute competency measure and supports caution in using raw LLM outputs for GE-specific protocol guidance.

We administer 45 validated psychometric questionnaires to 50 large language models (LLMs) to identify the dimensions along which LLMs differ psychometrically. Using Supervised Semantic Differential (SSD), we find that the primary axis of between-model variance separates items describing phenomenally rich experience, including embodied sensation, felt affect, inner speech, imagery, and empathy, from items describing stimulus-driven behavioral reactivity ($R^2_{adj}=.037$, $p<.0001$). To test this hypothesis at the item level, we introduce the Pinocchio score ($π_i$), the ratio of inter-model response variance under neutral prompting to that under a human-simulation prompt, as an annotation-free measure of each item's experiential demand. $π_i$ predicts condition-induced shifts in primary factor loading magnitudes ($ρ=-.215$, $p<.0001$, $n=1292$--$1310$ items), confirming that between-model divergence on experiential items is structured rather than noisy. Applying PCA to per-model EFA scores across all questionnaires reveals one dominant dimension, the Pinocchio Axis ($Π$): the degree to which a model presents itself as a locus of phenomenal experience rather than a system of behavioral responses. This axis captures 47.1% of cross-questionnaire between-model variance in primary factor scores and converges with item-level Pinocchio scores ($r=.864$). Marked within-provider divergence across closely related model variants is consistent with post-training fine-tuning as a key contributor, supporting the interpretation that $Π$ reflects a training-shaped self-representational tendency governing how a model treats experiential language as self-applicable. The dominant axis of between-model psychometric variation is therefore not a conventional personality trait but a self-representational stance toward one's own nature as an experiencer.

General-purpose LLMs with web search are increasingly used to scout the competitive landscape of pharmaceutical pipelines. We benchmark Gosset -- an AI platform with a chat interface backed by curated target-, modality-, and indication-level drug-asset annotations -- against four frontier systems with web access (Claude Opus 4.7, GPT 5.5, Gemini 3.1 Pro, Perplexity sonar-pro) on ten niche oncology/immunology targets where most of the pipeline lives in the long tail of preclinical and Asian-developed assets. All five systems receive the same natural-language query and the same JSON output schema. Across 10 targets Gosset returns 3.2x more verified drugs per query than the best frontier system, at perfect precision and 100% recall against the cross-system union of verified drugs. The same curated index is exposed as a Gosset MCP server that any frontier model can call as a tool, suggesting that each of these systems can close most of the recall gap by swapping generic web search for a curated index behind the same chat interface.

This position paper argues that the under-representation of social science tasks in contemporary LLM benchmarks limits advances in both LLM evaluation and social scientific inquiry. Benchmarks -- standardized tools for assessing computational systems -- are pivotal in the development of artificial intelligence (AI), including large language models (LLMs). Benchmarks do more than measure progress -- they actively structure it, shaping reputations, research agendas, and commercial outcomes. Despite this central role, the social sciences are largely absent from mainstream evaluation frameworks, even though scholars in these fields generate dozens of rigorously annotated, context-sensitive datasets each year. Integrating this work into benchmark design could significantly improve the generalization and robustness of AI models. In turn, models trained on social scientific tasks would likely yield better performance on classic and contemporary tasks in disciplines as diverse as history, sociology, political science or economics. This is all the more pressing as these disciplines are quickly turning to LLMs for assistance. To address this gap, we introduce BenCSSmark, a benchmark composed of datasets annotated by computational social scientists. By integrating social scientific perspectives into benchmarking, BenCSSmark seeks to promote more robust, transparent, and socially relevant AI systems and to foster efficient collaboration.