Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration

• URL: http://arxiv.org/abs/2609.12002v1
• Date: Thu, 10 Sep 2026 00:25:39 GMT
• Title: Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration
• Abstract summary: 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.
• Score: 0.5294698352039444
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: LLMs are increasingly used as automated judges for model training and evaluation, yet individual judges exhibit systematic biases that undermine reliability. Much of prior work has studied biases in pairwise LLM-as-a-judge settings; in this paper, we focus on absolute scoring tasks, which mirror more realistic use cases. Across four benchmarks and six models (36 judge-examinee pairs), we show that a model's task accuracy strongly predicts its judging accuracy (Pearson $r \geq 0.90$ on most models) and inversely predicts its directional bias ($r \leq -0.83$), but that accuracy alone does not ensure fair evaluation: more capable examinee models consistently receive more lenient judgments from all judges ($r \geq 0.83$). To address this, we propose calibrated weighted majority voting (WMV), an ensemble evaluation method that aggregates multiple LLM judges weighted by online estimates of their false-positive and false-negative rates. We introduce a disagreement-based estimator that derives these error rates purely from inter-judge agreement patterns, requiring no ground-truth labels or task metadata. In a simulated experiment with shifting task distributions, our label-free WMV tracks an oracle with perfect error-rate knowledge to within 0.5 percentage points on average, outperforming both individual judges and unweighted majority voting. These results demonstrate that principled multi-judge calibration can simultaneously improve accuracy and correct for systematic leniency without requiring labeled data, offering a scalable path to reliable automated evaluation as model capabilities increase.

Related papers

• Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges [3.974554103907186]
  We show that in multi-judge evaluation with labeled calibration data, do not discard weak judges by accuracy alone.<n>We explain this reversal with oracle analyses showing that the optimal calibrated risk under proper scoring rules cannot increase when additional judge signals are made available.
  arXiv  Detail & Related papers  (2026-05-10T18:49:58Z)
• Bias and Uncertainty in LLM-as-a-Judge Estimation [0.0]
  LLM-as-a-Judge evaluation has become a standard tool for assessing base model performance.<n>Recent work has proposed estimators to correct this bias, but their reliability depends critically on judge quality and, for model comparisons, on calibration stability.<n>We study these failure modes through analytical results, simulations over judge quality and cross-model calibration instability.
  arXiv  Detail & Related papers  (2026-05-07T20:55:21Z)
• CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation [6.3121191919394475]
  This work introduces a variance decomposition that partitions benchmark score variance into scenario, generation, judge, and residual components.<n>Based on this analysis, CyclicJudge, a round-robin assignment of judges to scenarios, is demonstrated to be the optimal strategy for a fixed judge-call budget.
  arXiv  Detail & Related papers  (2026-03-02T13:46:32Z)
• Who can we trust? LLM-as-a-jury for Comparative Assessment [42.32900791516691]
  Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment.<n>LLMs judges vary substantially in performance across tasks and aspects, and their judgment probabilities may be biased and inconsistent.<n>We propose BT-sigma, a judge-aware extension of the Bradley-Terry model that introduces a discriminator parameter for each judge to jointly infer item rankings and judge reliability from pairwise comparisons alone.
  arXiv  Detail & Related papers  (2026-02-18T17:04:02Z)
• A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth [4.9467757325435775]
  evaluating large language models (LLMs) on open-ended tasks is increasingly done via the LLM-as-a-judge paradigm.<n>Treating all judges equally can yield biased leaderboards and misleading uncertainty estimates.<n>We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters.
  arXiv  Detail & Related papers  (2026-01-29T15:01:28Z)
• Judging with Confidence: Calibrating Autoraters to Preference Distributions [56.17041629492863]
  We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population.<n>We present two learning methods tailored to different data conditions.<n>Our results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution.
  arXiv  Detail & Related papers  (2025-09-30T20:36:41Z)
• 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)
• CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards [72.44810390478229]
  CompassJudger-2 is a novel generalist judge model that overcomes limitations via a task-driven, multi-domain data curation strategy.<n> CompassJudger-2 achieves superior results across multiple judge and reward benchmarks.
  arXiv  Detail & Related papers  (2025-07-12T01:34:24Z)
• Quantitative LLM Judges [60.773734899532336]
  We propose quantitative LLM judges, which align evaluation scores of existing LLM judges to humans in a given domain.<n>The models are trained to improve the score of the original judge using its rationale and score.<n>Our experiments show that quantitative judges can improve the predictive power of existing judges through post-hoc modeling.
  arXiv  Detail & Related papers  (2025-06-03T14:44:23Z)
• JudgeBench: A Benchmark for Evaluating LLM-based Judges [61.048125269475854]
  JudgeBench is a benchmark for evaluating LLM-based judges on challenging response pairs spanning knowledge, reasoning, math, and coding.<n>Our comprehensive evaluation on a collection of prompted judges, fine-tuned judges, multi-agent judges, and reward models shows that JudgeBench poses a significantly greater challenge than previous benchmarks.
  arXiv  Detail & Related papers  (2024-10-16T17:58:19Z)
• Self-rationalization improves LLM as a fine-grained judge [21.917301609125417]
  We introduce Self-Rationalization, an iterative process of improving the rationales for the judge models. Self-rationalization works by having the model generate multiple judgments with rationales for the same input. We show that our model learns to produce higher quality rationales, with a win rate of $62%$ on average compared to models just trained via SFT on rationale.
  arXiv  Detail & Related papers  (2024-10-07T21:05:53Z)

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.