让角色扮演模型在知识外问题上仍保持一致，靠检索增强动态调整上下文。
Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations
- 基于检索增强生成，动态调整上下文以适应角色知识边界。
- 在976K字符的15个虚构角色数据集上，显著降低幻觉率，提升一致性。
- 无需训练，适合快速部署高保真角色扮演系统。
构建忠实模拟特定角色的对话代理（RPAs）仍具挑战性，因收集角色语料并持续更新参数成本高昂，故检索增强生成（RAG）成为必要手段。然而，现有研究对RAG-based RPAs关注甚少。我们发现，当角色缺乏与问题相关的知识时，基于RAG的代理易产生幻觉，难以生成准确回应。本文提出Amadeus——一种无需训练的框架，可在角色知识范围外仍显著提升角色一致性。此外，为支持此类代理的开发与严谨评估，我们人工构建CharacterRAG数据集，包含15位虚构角色的描述文档（共976K字符）及450组问答对。实验表明，该方法不仅能建模角色已知知识，还可有效捕捉个性等多维属性。
原文摘要 · Abstract (English)
Building role-playing agents (RPAs) that faithfully emulate specific characters remains challenging because collecting character-specific utterances and continually updating model parameters are resource-intensive, making retrieval-augmented generation (RAG) a practical necessity. However, despite the importance of RAG, there has been little research on RAG-based RPAs. For example, we empirically find that when a persona lacks knowledge relevant to a given query, RAG-based RPAs are prone to hallucination, making it challenging to generate accurate responses. In this paper, we propose Amadeus, a training-free framework that can significantly enhance persona consistency even when responding to questions that lie beyond a character's knowledge. In addition, to underpin the development and rigorous evaluation of RAG-based RPAs, we manually construct CharacterRAG, a role-playing dataset that consists of persona documents for 15 distinct fictional characters totaling 976K written characters, and 450 question-answer pairs. We find that our proposed method effectively models not only the knowledge possessed by characters, but also various attributes such as personality.
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。