Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation

• URL: http://arxiv.org/abs/2609.02942v1
• Date: Mon, 31 Aug 2026 18:40:58 GMT
• Title: Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation
• Abstract summary: We show that rubrics trained only on text, without access to any evaluated response, achieve nontrivial predictive performance on judge outputs.<n>Counterfactuals reveal that judges often fail to reliably update their decisions when either the candidate response or the rubric criterion is reversed.
• Score: 5.779889134811743
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-as-a-Judge pipelines are increasingly used to evaluate AI-generated text, based on the assumption that judgments arise from reasoning over candidate responses with respect to a rubric. We show that this assumption warrants further scrutiny. Classifiers trained only on rubric text, without access to any evaluated response, achieve nontrivial predictive performance on judge outputs. This suggests that rubric formulations encode recoverable evaluative signals, allowing scores to be partially anticipated independently of model outputs. Finally, counterfactual perturbations reveal that judges often fail to reliably update their decisions when either the candidate response or the rubric criterion is reversed. Our findings raise concerns about the reliability of rubric-based LLM evaluation and highlight the need for further methodological study of automated evaluation via LLMs.

Related papers

• On Evaluating LLM Alignment by Evaluating LLMs as Judges [68.15541137648721]
  evaluating large language models' (LLMs) alignment requires them to be helpful, honest, safe, and to precisely follow human instructions.<n>We examine the relationship between LLMs' generation and evaluation capabilities in aligning with human preferences.<n>We propose a benchmark that assesses alignment without directly evaluating model outputs.
  arXiv  Detail & Related papers  (2025-11-25T18:33:24Z)
• Bayesian Evaluation of Large Language Model Behavior [11.847752638476257]
  It is increasingly important to evaluate how text generation systems based on large language models behave.<n>Existing approaches to evaluation often neglect statistical uncertainty quantification.<n>We present two case studies applying a Bayesian approach for quantifying uncertainty in binary evaluation metrics.
  arXiv  Detail & Related papers  (2025-11-04T19:51:46Z)
• Analysis of instruction-based LLMs' capabilities to score and judge text-input problems in an academic setting [0.7699714865575188]
  Large language models (LLMs) can act as evaluators, a role studied by methods like LLM-as-a-Judge and fine-tuned judging LLMs.<n>We propose five evaluation systems that have been tested on a custom dataset of 110 answers about computer science from higher education students with three models: JudgeLM, Llama-3.1-8B and DeepSeek-R1-Distill-Llama-8B.<n>With the lowest median absolute deviation (0.945) and the lowest root mean square deviation (1.214) when compared to human evaluation, Reference Aided Evaluation offers fair scoring as well as insightful and complete evaluations
  arXiv  Detail & Related papers  (2025-09-25T10:26:23Z)
• RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning [64.46921169261852]
  RAG-Zeval is a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task.<n>Our approach trains evaluators with reinforcement learning, facilitating compact models to generate comprehensive and sound assessments.<n>Experiments demonstrate RAG-Zeval's superior performance, achieving the strongest correlation with human judgments.
  arXiv  Detail & Related papers  (2025-05-28T14:55:33Z)
• Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation [57.380464382910375]
  We show that the choice of feedback protocol for evaluation can significantly affect evaluation reliability and induce systematic biases.<n>We find that generator models can flip preferences by embedding distractor features.<n>We offer recommendations for choosing feedback protocols based on dataset characteristics and evaluation objectives.
  arXiv  Detail & Related papers  (2025-04-20T19:05:59Z)
• LLM-based relevance assessment still can't replace human relevance assessment [12.829823535454505]
  Recent studies suggest that large language models (LLMs) for relevance assessment in information retrieval provide comparable evaluations to human judgments.<n>Upadhyay et al. claim that LLM-based relevance assessments can fully replace traditional human relevance assessments in TREC-style evaluations.<n>This paper critically examines this claim, highlighting practical and theoretical limitations that undermine the validity of this conclusion.
  arXiv  Detail & Related papers  (2024-12-22T20:45:15Z)
• Towards Understanding the Robustness of LLM-based Evaluations under Perturbations [9.944512689015998]
  Large Language Models (LLMs) can serve as automatic evaluators for non-standardized metrics in summarization and dialog-based tasks.<n>We conduct experiments across multiple prompting strategies to examine how LLMs fare as quality evaluators when compared with human judgments.
  arXiv  Detail & Related papers  (2024-12-12T13:31:58Z)
• A Framework for Evaluating LLMs Under Task Indeterminacy [49.298107503257036]
  Large language model (LLM) evaluations often assume there is a single correct response -- a gold label -- for each item in the evaluation corpus. We develop a framework for evaluating LLMs under task indeterminacy.
  arXiv  Detail & Related papers  (2024-11-21T00:15:44Z)
• Evaluating the Retrieval Component in LLM-Based Question Answering Systems [1.7013938542585922]
  This study proposes a baseline for evaluating retrievers in Retrieval-Augmented Generation (RAG)-based chatbots. Our findings demonstrate that this evaluation framework provides a better image of how the retriever performs. Our method considers LLMs' strengths to ignore irrelevant contexts, as well as potential errors and hallucinations in their responses.
  arXiv  Detail & Related papers  (2024-06-10T16:46:22Z)
• DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
  Large Language Models (LLMs) are scalable and economical evaluators.<n>The question of how reliable these evaluators are has emerged as a crucial research question.<n>We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
  arXiv  Detail & Related papers  (2024-05-24T08:12:30Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.