Persona Authentication through Generative Dialogue
This addresses the problem of verifying persona models in dialogue systems, which is incremental as it builds on existing persona-based dialogue research.
The paper tackles the problem of persona authentication by learning a conversational policy to verify persona consistency, proposing a learning objective that maximizes mutual information between persona and dialogue, and developing a method that adaptively outputs personalized questions, with experiments showing it discovers effective question sequences that generalize to unseen personas.
In this paper we define and investigate the problem of \emph{persona authentication}: learning a conversational policy to verify the consistency of persona models. We propose a learning objective and prove (under some mild assumptions) that local density estimators trained under this objective maximize the mutual information between persona information and dialog trajectory. Based on the proposed objective, we develop a method of learning an authentication model that adaptively outputs personalized questions to reveal the underlying persona of its partner throughout the course of multi-turn conversation. Experiments show that our authentication method discovers effective question sequences that generalize to unseen persona profiles.