RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval
This addresses the issue of inconsistent character role-playing for users seeking immersive AI interactions, but it is incremental as it builds on existing retrieval methods.
The paper tackled the problem of LLMs generating irrelevant or inconsistent content in character imitation by proposing RoleRAG, a retrieval-based framework that integrates entity disambiguation and boundary-aware retrieval from a knowledge graph, resulting in better alignment with character knowledge and reduced hallucinations in role-playing benchmarks.
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.