检测大模型角色扮演中的知识错误，提升角色真实性。
Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing
- 构建新基准RoleKE-Bench评估模型识错能力
- 最新模型对熟悉知识错误识别率仍低
- 提出自回忆自质疑方法显著提升识错效果
大语言模型角色扮演日益受到关注，真实角色知识对构建可信代理至关重要。然而，现有研究普遍忽视模型在扮演过程中识别已知知识错误（KKE）和未知知识错误（UKE）的能力，导致角色可训练语料质量低下。本文提出RoleKE-Bench基准，用于评估模型在两类错误上的检测能力。结果表明，即使最新模型也难以有效识别这些错误，尤其在熟悉知识场景下表现不佳。我们实验了多种推理策略，提出基于智能体的自回忆自质疑（S²RD）方法，探索提升识错潜力。实验显示，该方法能有效增强模型检测角色知识错误的能力，但仍需持续关注。
原文摘要 · Abstract (English)
Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect these two types of errors effectively, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S$^2$RD), to explore further the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。