Persona-Aware Alignment Framework for Personalized Dialogue Generation
By: Guanrong Li , Xinyu Liu , Zhen Wu and more
Potential Business Impact:
Makes chatbots talk like specific people.
Personalized dialogue generation aims to leverage persona profiles and dialogue history to generate persona-relevant and consistent responses. Mainstream models typically rely on token-level language model training with persona dialogue data, such as Next Token Prediction, to implicitly achieve personalization, making these methods tend to neglect the given personas and generate generic responses. To address this issue, we propose a novel Persona-Aware Alignment Framework (PAL), which directly treats persona alignment as the training objective of dialogue generation. Specifically, PAL employs a two-stage training method including Persona-aware Learning and Persona Alignment, equipped with an easy-to-use inference strategy Select then Generate, to improve persona sensitivity and generate more persona-relevant responses at the semantics level. Through extensive experiments, we demonstrate that our framework outperforms many state-of-the-art personalized dialogue methods and large language models.
Similar Papers
Post Persona Alignment for Multi-Session Dialogue Generation
Computation and Language
Makes chatbots remember and act like you.
PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time
Artificial Intelligence
Makes AI understand and act like you.
Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
Computation and Language
Helps chatbots talk like you.