用知识图谱提升大模型角色扮演一致性
RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval
- 通过实体消歧和边界感知检索构建角色知识图谱
- 在角色扮演基准上降低幻觉率，提升角色一致性
- 适合需要精准角色模拟的对话系统开发者
大语言模型在角色模仿方面展现出潜力，能实现沉浸式对话。然而，其生成内容常与角色背景不符。我们将其归因于：（1）因实体歧义导致角色知识召回不准；（2）缺乏对角色认知边界的意识。为此，我们提出 RoleRAG，一种基于检索的框架，结合高效的实体消歧进行知识索引，并采用边界感知检索器从结构化知识图谱中提取上下文相关的信息。在角色扮演基准上的实验表明，RoleRAG 的校准检索使通用和专用语言模型更贴合角色知识，减少幻觉响应。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown promise in character imitation, enabling immersive and engaging conversations. However, they often generate content that is irrelevant or inconsistent with a character's background. We attribute these failures to: (1) the inability to accurately recall character-specific knowledge due to entity ambiguity, and (2) a lack of awareness of the character's cognitive boundaries. To address these issues, we propose RoleRAG, a retrieval-based framework that integrates efficient entity disambiguation for knowledge indexing with a boundary-aware retriever for extracting contextually appropriate information from a structured knowledge graph. Experiments on role-playing benchmarks show that RoleRAG's calibrated retrieval helps both general-purpose and role-specific LLMs better align with character knowledge and reduce hallucinated responses.
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。