arXiv:2606. 09409v1 Announce Type: new Abstract: Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they reward superficial stylistic cues or display judge biases.
arXiv:2601. 21817v2 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm.
Large Language Model judges are commonly used to rank texts via pairwise comparison, with reliability traditionally measured by position bias, transitivity, and pairwise agreement. This paper argues that these proxies are misleading because they are dominated by close‑rank‑gap pairs, which contribute little to the overall ranking, while far‑gap pairs carry the true ranking signal. Experiments on simulations and human‑rated corpora show weak correlation between the proxies and actual ranking accuracy, suggesting judges should be evaluated using rank‑gap‑conditional metrics against human rankings.
arXiv:2607. 02104v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers.
The study investigates bias in large language model (LLM) judges by having ten LLMs evaluate narrative constraint selections rather than generated text. Results show that self-preference largely disappears under blind evaluation when quality and evaluator severity are controlled, but self- and other-labels alone shift scores bidirectionally when quality is matched. The authors conclude that authorship attribution drives evaluation bias and that open-ended, ground‑truth‑free tasks can effectively study LLM judge behavior.
arXiv:2607. 28282v1 Announce Type: cross Abstract: Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive.
arXiv:2606. 13221v2 Announce Type: replace Abstract: Evaluating new large language models typically requires costly human annotation campaigns at scale.
The paper argues that the current LLM-as-a-judge evaluation method, which compensates for systematic measurement bias by increasing the number of comparisons, is statistically unsound and computationally wasteful. It identifies that treating LLM judges as neutral ignores documented biases such as position bias, verbosity bias, judge severity, and self‑enhancement. The authors propose a unified latent variable framework that jointly models pairwise and ordinal data while explicitly correcting for these confounders, enabling reliable rankings with far fewer comparisons and negligible additional compute.
arXiv:2609.15561v1 Announce Type: new Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?...
arXiv:2606. 05308v1 Announce Type: new Abstract: With PRECISE, we extended Prediction-Powered Inference to produce bias-corrected estimates of ranking evaluation metrics by combining a small human-labeled set with a large LLM-judged set.
arXiv:2603.00039v2 Announce Type: replace-cross Abstract: LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw:...
JudgeProfile is a framework that analyzes the subjectivity of large language model (LLM) judges by separating evaluation into perception—how judges compare responses on attributes such as clarity, correctness, and detail—and prioritization—how much each attribute influences the final decision. Using the curated SubjectiveSet dataset of 50,013 response pairs evaluated by 21 judges across 87 attributes, the study finds that judges often agree on attribute judgments even when their overall choices differ. By estimating and adjusting attribute weights, the authors improve agreement with reference labels from 66.48% to 71.97%, outperforming fine‑tuning and rubric prompting.
The paper examines LLM-as-a-Judge systems used to assess AI-generated text, questioning the assumption that judgments are derived from reasoning over responses and rubrics. It finds that classifiers trained solely on rubric text can predict judge outputs, indicating that rubrics contain recoverable evaluative signals independent of the responses. Counterfactual experiments show judges often fail to adjust decisions when either the response or rubric criterion is reversed, raising doubts about the reliability of rubric-based LLM evaluation.