Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation

The paper examines how large language models (LLMs) tend to overuse persona attributes in persona-based dialogue generation, producing unnatural responses. It identifies a systematic bias in LLMs to incorporate all provided persona details and shows that current metrics cannot assess contextual appropriateness. To address this, the authors introduce Self-CONtrastive Persona Overuse Suppression (SCONPOS), which intervenes in the prompt encoding stage to reduce overuse, and propose the Persona Appropriateness Score (PAS), a new metric that penalizes both overuse and underuse of persona attributes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• safety