arXiv:2610.28522v1 Announce Type: new Abstract: Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make...
The paper introduces an audit layer for vision‑language model benchmarks that reuses per‑question artifacts from evaluation runs to assess the benchmark itself. Six detectors analyze saved outputs, and an additional text‑only rerun removes visual inputs to produce per‑question reports and aggregate statistics, including permutation‑null excess and interval estimates. Applying this method to the MMStar benchmark reveals that 20.2% of its questions show no accuracy gain from images, with a small but significant excess in mathematics and science categories, and identifies questions where all models chose the same non‑gold option.
arXiv:2610.05094v1 Announce Type: cross Abstract: Researchers increasingly use Large Language Models as judges (LLM-as-a-judge) to evaluate model outputs. Yet there are no standards for how to design...
The paper investigates how large language models (LLMs) used as judges in absolute scoring tasks exhibit systematic biases that compromise reliability. It shows that a judge’s task accuracy strongly predicts both its judging accuracy and its directional bias, yet more capable examinee models consistently receive more lenient judgments. To mitigate these biases, the authors propose a calibrated weighted majority voting (WMV) ensemble that estimates judges’ error rates from inter-judge agreement patterns, achieving near-oracle performance without labeled data and improving both accuracy and fairness.
The paper introduces the Grounded Integration Measure (GIM), a benchmark of 820 expert‑authored problems designed to test models on tasks that integrate multiple cognitive operations such as constraint satisfaction, state tracking, epistemic vigilance, and audience calibration. GIM emphasizes realistic, broadly accessible knowledge rather than specialized expertise, and uses a judge‑aware 2‑parameter logistic IRT model to produce robust ability estimates across 53 model‑thinking‑level configurations. The authors provide a comprehensive leaderboard of 22 models and 47 test configurations, and conduct an extensive study on how test‑time compute affects model capability, finding that configuration choices like thinking budget and quantization can be as influential as model selection itself. whyItMatters":"By focusing on integration of multiple cognitive domains, GIM offers a more realistic assessment of model reasoning capabilities than benchmarks that either overemphasize memorization or abstract reasoning alone."
arXiv:2603. 00077v3 Announce Type: replace-cross Abstract: Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduced to exact programmatic checks.
The paper introduces Conditional Accuracy Profiling (CAP), a diagnostic framework that breaks down LLM‑judge accuracy into eight deployment conditions covering content sensitivity, robustness, and rationale quality. CAP is benchmark‑agnostic and can be applied directly when annotations are available, via task‑subset proxies, or through controlled augmentation. Applied to seven judges across six benchmarks, CAP reveals that aggregate accuracy masks important differences—for example, judges highly sensitive to omitted qualifications rank poorly on a Hard‑Constructed subset, and Position Robustness is generally stable but can degrade sharply under adversarial stress.
The paper introduces VTC-Bench, a five‑domain benchmark designed to evaluate multiple outputs from large language models (LLMs) by measuring Validated Task Coverage (VTC). VTC quantifies how many distinct, useful results are produced within a set number of attempts, using real‑data tasks that allow automatic, reproducible checks of output quality and task‑relevant distinctness without relying on model‑based judges. Experiments show that models which perform best on single‑draw quality do not always achieve the highest coverage, and simple output‑variation metrics fail to capture task‑relevant diversity, highlighting the importance of evaluating finite candidate sets directly.
arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.
arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.
SkillEval introduces a new evaluation framework for large language models that moves beyond single scalar scores to perform cross-model, skill-level analysis. It automatically discovers interpretable skills from benchmark questions using LLM meta‑cognition and applies cognitive diagnosis models to estimate per‑skill abilities. Experiments on 3,811 LLMs across five benchmarks show that SkillEval yields more calibrated, informative model profiles, enabling tasks such as efficient LLM routing and adaptive testing.
arXiv:2610.02267v1 Announce Type: new Abstract: Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input...