通过基于群体的轮询缓解大语言模型中的判断偏好偏差
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
AI总结：
本文提出Genii框架，通过多智能体协作优化缓解LLM判断偏好偏差，无需人工标注数据，提升评估性能。
摘要：
大型语言模型（LLM）作为自动评估者，即LLM-as-a-Judge，已引起广泛关注。此方法在对齐LLM与人类判断中起关键作用，提供准确可靠评估。然而，基于LLM的判断模型在评估阶段常表现出判断偏好偏差，倾向于自身生成的响应，影响判断可靠性。本文引入基于群体的轮询优化（Genii），一种无监督的多智能体协作优化框架，以缓解判断模型的内在判断偏好偏差。具体而言，Genii将各种基于LLM的判断模型整合到多智能体系统中，并模拟交互式的客户端-服务器轮询机制，以无监督的方式优化每个客户端智能体。实验表明，Genii在无需人工标注数据的情况下，优于基于标注判断数据训练的监督模型。Genii在不同客户端智能体轮询过程中持续提升性能，即使较弱的模型作为服务器智能体时也是如此。进一步分析表明，Genii有效缓解了基于LLM的判断模型的判断偏好偏差，证明了其有效性。所有代码可在https://github.com/NEUIR/Genii获取。
英文摘要：
Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LLMs with human judgments, providing accurate and reliable assessments. However, LLM-based judgment models often exhibit judgment preference bias during the evaluation phase, tending to favor responses generated by themselves, undermining the reliability of their judgments. This paper introduces the Group-Based Polling Optimization (Genii), an unsupervised multi-agent collaborative optimization framework that mitigates the inherent judgment preference bias of judgment models. Specifically, Genii integrates various LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism to optimize each client agent unsupervisedly. Our experiments demonstrate that Genii outperforms supervised models trained on annotated judgment data, while requiring no human-labeled annotations. Genii consistently improves performance across different client agents during the polling, even when weaker models act as server agents. Further analysis reveals that Genii effectively mitigates judgment preference bias of LLM-based judgment models, demonstrating its effectiveness. All codes are available at https://github.com/NEUIR/Genii.
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。
