Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations

• URL: http://arxiv.org/abs/2508.21164v3
• Date: Thu, 09 Oct 2025 20:01:01 GMT
• Title: Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
• Abstract summary: Large language models (LLMs) are increasingly deployed as evaluators of text quality.<n>This study investigates systematic bias in self- and cross-model evaluations across three prominent LLMs: ChatGPT, Gemini, and Claude.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed as evaluators of text quality, yet the validity of their judgments remains underexplored. This study investigates systematic bias in self- and cross-model evaluations across three prominent LLMs: ChatGPT, Gemini, and Claude. We designed a controlled experiment in which blog posts authored by each model were evaluated by all three models under four labeling conditions: no attribution, true attribution, and two false-attribution scenarios. Evaluations employed both holistic preference voting and granular quality ratings across three dimensions Coherence, Informativeness, and Conciseness with all scores normalized to percentages for direct comparison. Our findings reveal pronounced asymmetries in model judgments: the "Claude" label consistently elevated scores regardless of actual authorship, while the "Gemini" label systematically depressed them. False attribution frequently reversed preference rankings, producing shifts of up to 50 percentage points in voting outcomes and up to 12 percentage points in quality ratings. Notably, Gemini exhibited severe self-deprecation under true labels, while Claude demonstrated intensified self-preference. These results demonstrate that perceived model identity can substantially distort both high-level judgments and fine-grained quality assessments, independent of content quality. Our findings challenge the reliability of LLM-as-judge paradigms and underscore the critical need for blind evaluation protocols and diverse multi-model validation frameworks to ensure fairness and validity in automated text evaluation and LLM benchmarking.

Related papers

• Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration [0.5294698352039444]
  We study absolute scoring tasks, which mirror more realistic use cases.<n>We show that a model's task accuracy strongly predicts its judging accuracy.<n>More capable examinee models consistently receive more lenient judgments from all judges.
  arXiv  Detail & Related papers  (2026-09-10T00:25:39Z)
• Local Brushstroke Quality Assessment via Vision-Language Feedback [16.561215035945423]
  This paper investigates whether multimodal LLMs can evaluate local brushstroke quality in calligraphy and generate educationally useful natural language feedback.<n>We construct an evaluation framework in which three multimodal LLMs assess before-after image pairs of calligraphic works using a five-point ordinal scale, and compare their outputs against scores assigned by three expert calligraphers.<n>We additionally examine a Retrieval-Augmented Generation (RAG) variant of Claude as a preliminary condition. Results show that all models achieve useful levels of absolute score accuracy (MAE), with GPT-4o performing best (MAE = 0.885)
  arXiv  Detail & Related papers  (2026-07-15T18:22:21Z)
• DualEval: Joint Model-Item Calibration for Unified LLM Evaluation [67.99119926012686]
  DualEval is a latent model-item calibration framework that represents models and evaluation items in a shared space.<n>We apply DualEval across four domains: coding, math, miscellaneous domain-knowledge tasks, and generic everyday user queries.
  arXiv  Detail & Related papers  (2026-06-24T22:40:46Z)
• Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems [32.83708359216193]
  Large Language Models (LLMs) are increasingly being used to autonomously evaluate the quality of content in communication systems.<n>This paper systematically investigates judgment biases in two LLM-as-a-judge models under the point-wise scoring setting.<n>We propose four potential mitigation strategies to ensure fair and reliable AI judging in practical communication scenarios.
  arXiv  Detail & Related papers  (2025-10-14T12:52:29Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• EigenBench: A Comparative Behavioral Measure of Value Alignment [0.28707625120094377]
  EigenBench is a black-box method for benchmarking language models' values.<n>It is designed to quantify subjective traits for which reasonable judges may disagree on the correct label.<n>It can recover model rankings on the GPQA benchmark without access to objective labels.
  arXiv  Detail & Related papers  (2025-09-02T04:14:26Z)
• Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge [17.40713507922006]
  Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other outputs.<n>LLMs may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias.<n>We present a statistical framework that explicitly formalizes assumptions under which self-bias can be identified and estimated.
  arXiv  Detail & Related papers  (2025-08-08T21:22:12Z)
• LLMEval-3: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models [51.55869466207234]
  Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting.<n>We introduce LLMEval-3, a framework for dynamic evaluation of LLMs.<n>LLEval-3 is built on a proprietary bank of 220k graduate-level questions, from which it dynamically samples unseen test sets for each evaluation run.
  arXiv  Detail & Related papers  (2025-08-07T14:46:30Z)
• Evaluating Scoring Bias in LLM-as-a-Judge [8.67484421243584]
  Large Language Models (LLMs) are employed as evaluators for complex tasks.<n>There are various biases within LLM-as-a-Judge, which adversely affect the fairness and reliability of judgments.
  arXiv  Detail & Related papers  (2025-06-27T15:25:23Z)
• Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications [0.7124971549479361]
  This study introduces a framework for evaluating consistency in large language model (LLM) binary text classification.<n>We determine sample size requirements, develop metrics for invalid responses, and evaluate intra- and inter-rater reliability.
  arXiv  Detail & Related papers  (2025-05-20T21:12:58Z)
• 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)
• The Tile: A 2D Map of Ranking Scores for Two-Class Classification [10.89980029564174]
  We present a novel versatile tool, named the Tile, that organizes an infinity of ranking scores in a single 2D map for two-class classifiers.<n>We study the properties of the underlying ranking scores, such as the influence of the priors or the correspondences with the ROC space.
  arXiv  Detail & Related papers  (2024-12-05T16:27:59Z)
• Reducing Biases in Record Matching Through Scores Calibration [1.5530839016602822]
  We propose a threshold-independent framework for measuring and reducing score bias.<n>We show that several state-of-the-art matching methods exhibit substantial score bias, even when appearing fair under standard threshold-based metrics.<n>We introduce two post-processing score calibration algorithms. The first, calib, aligns group-wise score distributions using the Wasserstein barycenter, targeting demographic parity.<n>The second, ccalib, conditions on predicted labels to further reduce label-dependent biases, such as equal opportunity.
  arXiv  Detail & Related papers  (2024-11-03T21:01:40Z)
• Online Multi-Label Classification under Noisy and Changing Label Distribution [9.17381554071824]
  We propose an online multi-label classification algorithm under Noisy and Changing Label Distribution (NCLD) The objective is to simultaneously model the label scoring and the label ranking for high accuracy, whose robustness to NCLD benefits from three novel works.
  arXiv  Detail & Related papers  (2024-10-03T11:16:43Z)
• Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery [56.172872410834664]
  Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning. We propose a Memory Consistency guided Divide-and-conquer Learning framework (MCDL) Our method outperforms state-of-the-art models by a large margin on both seen and unseen classes of the generic image recognition.
  arXiv  Detail & Related papers  (2024-01-24T09:39:45Z)
• 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)
• Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings [63.35165397320137]
  This study investigates the consistency of feedback ratings generated by OpenAI's GPT-4. The model rated responses to tasks within the Higher Education subject domain of macroeconomics in terms of their content and style.
  arXiv  Detail & Related papers  (2023-08-03T12:47:17Z)
• Large Language Models are not Fair Evaluators [60.27164804083752]
  We find that the quality ranking of candidate responses can be easily hacked by altering their order of appearance in the context. This manipulation allows us to skew the evaluation result, making one model appear considerably superior to the other. We propose a framework with three simple yet effective strategies to mitigate this issue.
  arXiv  Detail & Related papers  (2023-05-29T07:41:03Z)
• Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification [85.76130799062379]
  We study how false negative labels affect the model's explanation. We propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels.
  arXiv  Detail & Related papers  (2023-04-04T14:00:59Z)
• Debiased Contrastive Learning [64.98602526764599]
  We develop a debiased contrastive objective that corrects for the sampling of same-label datapoints. Empirically, the proposed objective consistently outperforms the state-of-the-art for representation learning in vision, language, and reinforcement learning benchmarks.
  arXiv  Detail & Related papers  (2020-07-01T04:25:24Z)

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.