迈向鲁棒的基于大语言模型的裁判：偏见评估与去偏优化
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
AI总结：
本文提出JudgeBiasBench，通过系统量化LLM裁判偏见，提出偏见感知训练方法，减少偏见并保持评估能力。
摘要：
基于大语言模型（LLM）的裁判被广泛用于自动化评估和奖励建模，但其判断常常受到判断偏见的影响。准确评估这些偏见对于确保LLM基于裁判的可靠性至关重要。然而，现有研究通常在单一裁判公式下研究有限的偏见，缺乏全面的评估。为弥合这一差距，我们提出了JudgeBiasBench，一个用于系统量化LLM基于裁判偏见的基准。JudgeBiasBench在四个维度上定义了判断偏见的分类，并通过受控的偏见注入管道构建偏见增强的评估实例，涵盖12种代表性偏见类型。我们进行了广泛的实验，涵盖生成式和判别式裁判，揭示了当前裁判存在显著且多样的偏见模式，往往损害自动化评估的可靠性。为缓解判断偏见，我们提出了一种偏见感知训练，明确将偏见相关属性纳入训练过程，鼓励裁判将任务相关质量与偏见相关线索区分开来。通过采用强化学习用于生成式裁判和对比学习用于判别式裁判，我们的方法有效减少了判断偏见，同时在很大程度上保持了通用评估能力。
英文摘要：
Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biases is essential for ensuring the reliability of LLM-based judges. However, existing studies typically investigate limited biases under a single judge formulation, either generative or discriminative, lacking a comprehensive evaluation. To bridge this gap, we propose JudgeBiasBench, a benchmark for systematically quantifying biases in LLM-based judges. JudgeBiasBench defines a taxonomy of judgment biases across 4 dimensions, and constructs bias-augmented evaluation instances through a controlled bias injection pipeline, covering 12 representative bias types. We conduct extensive experiments across both generative and discriminative judges, revealing that current judges exhibit significant and diverse bias patterns that often compromise the reliability of automated evaluation. To mitigate judgment bias, we propose bias-aware training that explicitly incorporates bias-related attributes into the training process, encouraging judges to disentangle task-relevant quality from bias-correlated cues. By adopting reinforcement learning for generative judges and contrastive learning for discriminative judges, our methods effectively reduce judgment biases while largely preserving general evaluation capability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
