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

Jeiyoon Park, Yongshin Han, Minseop Kim, Kisu Yang

Keywords: Large Language Model, Role-playing Agents, Retrieval-augmented Generation

TL;DR: A persona-consistent, RAG-based role-playing agent that can handle questions outside its knowledge base.

Abstract: Recent advances in large language models (LLMs) have catalyzed research on role-playing agents (RPAs). However, the process of collecting character-specific utterances and continually updating model parameters to track rapidly changing persona attributes is resource-intensive. Although retrieval-augmented generation (RAG) can alleviate this problem, if a persona does not contain 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. Amadeus is composed of Adaptive Context-aware Text Splitter (ACTS), Guided Selection (GS), and Attribute Extractor (AE). To facilitate effective RAG-based role-playing, ACTS partitions each character’s persona into optimally sized, overlapping chunks and augments this representation with hierarchical contextual information. AE identifies a character's general attributes from the chunks retrieved by GS and uses these attributes as a final context to maintain robust persona consistency even when answering out-of-knowledge questions. 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.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 7010