arXiv:2609.13824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faste...
The paper introduces a two‑dimensional construct validity framework for evaluating large language models (LLMs) as judges, defining invariance (S) and sensitivity (R) to construct‑preserving and construct‑changing edits. Experiments across seven judges and four domains reveal high invariance (average S = 0.945) but low sensitivity (average R = 0.319), with sensitivity varying by edit type. Audits of public label sets show that surface‑only predictors can reproduce a substantial portion of labels, underscoring that high agreement does not guarantee construct validity.
arXiv:2608.28626v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate peer reviews, prompting examination of their capacity for critical evaluation. This st...
The paper investigates whether consensus among large language model (LLM) judges truly reflects human alignment. By treating each judge’s scores as vectors, the authors measure spread, effective rank, and angles to human scores across 42 judges on Indic benchmarks, revealing that inter‑judge agreement often mirrors shared blind spots rather than human judgments. They find that while judges agree as much as humans, they only reach 58‑66% of human agreement and frequently focus on axes humans do not weight, indicating that ensemble agreement alone is insufficient evidence of alignment.
arXiv:2606. 09843v3 Announce Type: replace-cross Abstract: Large language models (LLMs) give stable answers to personality questionnaires, yet these self-reports fail to predict how the models behave.
The study evaluates a label‑free rubric‑clarification procedure that rewrites only the most contested sub‑criteria of a rubric, aiming to reduce disagreement among large‑language‑model (LLM) judges. Across six rubric conditions and three datasets (SummEval, HealthBench, USR Topical‑Chat), the method increased inter‑judge agreement on SummEval by 0.069 Krippendorff’s α, but did not improve agreement with human expert ratings. In other datasets, neither inter‑judge nor human agreement met the preregistered effect criteria, and human agreement was actually lower after editing contested clauses compared to random edits.
arXiv:2608.22432v1 Announce Type: cross Abstract: Multilingual LLM judges produce different evaluator-backbone rankings depending on the prompt language: on an eight-language Agent-as-a-Judge benchma...
The paper investigates how well large language models (LLMs) can serve as judges in summarization evaluation by applying psychometric techniques. Using Many‑Facet Rasch Models, the authors decompose human and LLM ratings into latent summary quality, rater severity, dimension severity, and rating‑scale thresholds, and introduce a residual hardness metric to capture judging difficulty. Their analysis of 17 open‑weight LLM judges on the SummEval dataset reveals that moderate alignment in latent quality does not translate to alignment in residual hardness; humans and LLMs differ in which summary–dimension units are hard, with LLMs tending to find consistency hard and humans tending to find coherence hard, and some hard cases can be predicted from observable source–summary properties.
arXiv:2609.21277v1 Announce Type: cross Abstract: How many human judgments does a panel of language models represent? The answer depends on what is matched. We audit categorical judge panels against...
arXiv:2608. 14606v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations ask whether answers look plausible at the individual level.
The paper discusses how large language models (LLMs) are used in various evaluation roles—examining benchmarks, judging other models, and rating human content—and frames each as a measurement problem. It proposes using Rasch measurement theory (RMT) to decompose ordinal ratings into distinct facets on a common scale, offering diagnostics for miscalibration and rater bias. A case study applying RMT to the Measuring Hate Speech corpus reveals systematic differences between LLMs and human raters in severity, calibration, robustness, sensitivity, and scale use, suggesting RMT should be part of the evaluation toolkit for LLMs in all roles.
arXiv:2609.13773v1 Announce Type: new Abstract: LLM-as-a-Judge evaluators are increasingly used to score open-ended generation, yet a judge's correlation with human ratings on its development set may...