arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2508.02016cs.AI
收藏

动态上下文适应用于具有检索增强生成的连贯角色扮演代理

Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations

SOOP;Korea University(韩国大学)

Jeiyoon Park, Yongshin Han, Minseop Kim, Kisu Yang

AI总结:

本文提出Amadeus框架,通过动态上下文适应提升角色扮演代理在知识外延问题中的连贯性,并构建CharacterRAG数据集以支持RAG基于角色扮演代理的开发与评估。

摘要:

构建能够忠实模拟特定角色的角色扮演代理(RPAs)仍然具有挑战性,因为收集角色特定的发言和持续更新模型参数是资源密集型的,使检索增强生成(RAG)成为一种实用的必要条件。然而,尽管RAG的重要性,针对基于RAG的角色扮演代理的研究仍然有限。例如,我们实证发现,当一个角色缺乏与给定查询相关知识时,基于RAG的角色扮演代理容易产生幻觉,这使得生成准确的响应具有挑战性。在本文中,我们提出了Amadeus,一个无需训练的框架,能够在回答超出角色知识范围的问题时显著增强角色一致性。此外,为了支撑基于RAG的角色扮演代理的发展和严格评估,我们手动构建了CharacterRAG,一个包含15个不同虚构角色的个人文档总共有976,000个字符,以及450个问题-答案对的角色扮演数据集。我们发现,所提出的方法不仅能够建模角色所拥有的知识,还能建模各种属性,如个性。

英文摘要:

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.

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。

↑