Mitigating Hallucination in Fictional Character Role-Play
Abstract: Role-playing has wide-ranging applications in customer support, embodied agents, computational social science, etc. The influence of parametric world knowledge of large language models (LLMs) often causes role-playing characters to act out of character and hallucinate about things outside the scope of their knowledge. In this work, we focus on the evaluation and mitigation of hallucination in fictional character role-play. We introduce a dataset with more than 2,000 characters and 72,000 interviews, including 18,000 adversarial questions. We propose RoleFact, a role-playing method that mitigates hallucination by modulating the influence of parametric knowledge using a pre-calibrated confidence threshold. Experiments show that the proposed method improves the factual precision of generated responses by 18% for adversarial questions with a 44% reduction in temporal hallucination for time-sensitive interviews. We will make the dataset and code publicly available for the research community upon acceptance.
Paper Type: Long
Research Area: Dialogue and Interactive Systems
Research Area Keywords: factuality,retrieval-augmented generation
Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources
Languages Studied: English
Submission Number: 4477
Loading