任何大语言模型都能成为可靠的评判者：用基于推理的偏差检测器去偏差
Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
AI总结：
针对大语言模型作为评判者时存在的评估偏差问题，提出即插即用的基于推理的偏差检测器RBD，通过外部迭代的偏差检测与反馈修正引导评判者自我校正，在多类偏差、多评判模型上显著提升评估准确率与一致性，且具备良好的泛化性与可扩展性。
摘要：
大语言模型作为评判者（LLM-as-a-Judge）已成为自动评估生成内容的一种极具前景的工具，但其可靠性常因评判中存在的潜在偏差而受损。现有缓解这些偏差的方法存在关键局限：基于上下文学习的方法因评判者自我反思能力有限，无法解决根深蒂固的偏差；而微调方法并不适用于所有类型的评判者，尤其是闭源模型。为应对这一挑战，我们提出了基于推理的偏差检测器（Reasoning-based Bias Detector，RBD），这是一个可即插即用的模块，能够识别有偏差的评估结果，并生成结构化推理以引导评判者自我修正。RBD无需修改评判者本身，而是作为外部模块运行，采用偏差检测与反馈驱动修正的迭代流程。为支撑其开发，我们设计了一套完整的流程，包括偏差数据集构建、监督数据采集、RBD的蒸馏式基于推理微调，以及与大语言模型评判者的集成。我们微调了四种规模的RBD模型，参数量从15亿到140亿不等，且在所有规模上均观察到性能的一致提升。在8个大语言模型评判者上针对4种偏差类型（冗长偏差、位置偏差、从众偏差、情感偏差）开展的实验结果证明了RBD的显著有效性。例如，RBD-8B模型将评估准确率平均提升了18.5%，一致性提升了10.9%，分别比基于提示的基线方法和经过微调的评判者高出12.8%和17.2%。这些结果凸显了RBD的有效性与可扩展性。额外实验进一步证明了其在不同偏差类型和领域间的强泛化能力，以及高效性。
英文摘要：
LLM-as-a-Judge has emerged as a promising tool for automatically evaluating generated outputs, but its reliability is often undermined by potential biases in judgment. Existing efforts to mitigate these biases face key limitations: in-context learning-based methods fail to address rooted biases due to the evaluator's limited capacity for self-reflection, whereas fine-tuning is not applicable to all evaluator types, especially closed-source models. To address this challenge, we introduce the Reasoning-based Bias Detector (RBD), which is a plug-in module that identifies biased evaluations and generates structured reasoning to guide evaluator self-correction. Rather than modifying the evaluator itself, RBD operates externally and engages in an iterative process of bias detection and feedback-driven revision. To support its development, we design a complete pipeline consisting of biased dataset construction, supervision collection, distilled reasoning-based fine-tuning of RBD, and integration with LLM evaluators. We fine-tune four sizes of RBD models, ranging from 1.5B to 14B, and observe consistent performance improvements across all scales. Experimental results on 4 bias types--verbosity, position, bandwagon, and sentiment--evaluated using 8 LLM evaluators demonstrate RBD's strong effectiveness. For example, the RBD-8B model improves evaluation accuracy by an average of 18.5% and consistency by 10.9%, and surpasses prompting-based baselines and fine-tuned judges by 12.8% and 17.2%, respectively. These results highlight RBD's effectiveness and scalability. Additional experiments further demonstrate its strong generalization across biases and domains, as well as its efficiency.
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。
