Get Started
Research questionHow can persona-based dialogue systems use persona information only when it is relevant to the conversation?Dialogue models may insert every supplied persona detail even when it does not fit the exchange, making responses unnatural. Evaluation must distinguish appropriate use from both persona overuse and omission.
AI
Evaluation & Benchmarks
Natural Language Processing
Latest papersRecent research connected to this question, newest first.Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue GenerationThe source evaluates a prompt-encoding intervention and an assessment score intended to capture both overuse and underuse in LLM-based persona dialogue. The intervention operates on internal representations rather than through an ordinary text-only API, and the evidence is limited to the reported experiments.research paper · Sep 4, 2026
Related questions
How can personalized dialogue agents keep evolving user personas traceable to supporting events during retrieval?When does persona prompting improve LLM survey-response prediction, and how should attributes be selected?How can controlled synthetic dialogues satisfy intended emotion and intent while remaining natural to human readers?How can assistants identify when a request conflicts with implicit user-specific circumstances?
Home
Topics
Search
Library