评判裁判：评估LLM作为裁判的对齐性与脆弱性
Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
AI总结：
本文系统评估了13个LLM裁判模型在人类一致性高的场景下评判9个考生模型答案的表现，发现仅最大模型对齐较好但仍落后于人类间一致性，并揭示了裁判对提示复杂度敏感和评分宽松等脆弱性。
摘要：
作为一种有望解决人类评估可扩展性挑战的方案，LLM作为裁判的范式正迅速获得关注，成为评估大型语言模型（LLMs）的一种方法。然而，关于这一范式的优势与劣势，以及它可能存在的潜在偏见，仍有许多未解之谜。在本文中，我们对各种LLM作为裁判的表现进行了全面研究，重点关注一个人类间一致性较高的干净场景。通过研究十三个不同模型规模和家族的裁判模型，对九个不同的“考生模型”（包括基础模型和指令微调模型）的答案进行评判，我们发现只有最好的（也是最大的）模型才能实现与人类的合理对齐。然而，它们仍然远落后于人类间一致性，并且它们给出的分数与人类给出的分数仍可能相差多达5分。在它们对九个考生模型的排名方面，较小的模型甚至词汇度量指标contains也可能提供合理的信号。通过错误分析和其他研究，我们识别出裁判模型中的脆弱性，例如它们对提示复杂性和长度的敏感性，以及倾向于宽松评分的趋势。即使是最好的裁判在这个相对简单的设置中也与人类存在差异，这一事实表明，在更复杂的设置中使用裁判时保持谨慎可能是明智的。最后，我们的研究重新发现了使用超越简单百分比对齐的对齐度量的重要性，表明具有高百分比一致性的裁判仍然可能给出截然不同的分数。
英文摘要：
Offering a promising solution to the scalability challenges associated with human evaluation, the LLM-as-a-judge paradigm is rapidly gaining traction as an approach to evaluating large language models (LLMs). However, there are still many open questions about the strengths and weaknesses of this paradigm, and what potential biases it may hold. In this paper, we present a comprehensive study of the performance of various LLMs acting as judges, focusing on a clean scenario in which inter-human agreement is high. Investigating thirteen judge models of different model sizes and families, judging answers of nine different 'examtaker models' - both base and instruction-tuned - we find that only the best (and largest) models achieve reasonable alignment with humans. However, they are still quite far behind inter-human agreement and their assigned scores may still differ with up to 5 points from human-assigned scores. In terms of their ranking of the nine exam-taker models, instead, also smaller models and even the lexical metric contains may provide a reasonable signal. Through error analysis and other studies, we identify vulnerabilities in judge models, such as their sensitivity to prompt complexity and length, and a tendency toward leniency. The fact that even the best judges differ from humans in this comparatively simple setup suggest that caution may be wise when using judges in more complex setups. Lastly, our research rediscovers the importance of using alignment metrics beyond simple percent alignment, showing that judges with high percent agreement can still assign vastly different scores.
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。
