Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach
This work addresses the need for more effective emotional support in AI-driven conversations, offering a novel approach to guide emotional transitions, though it is incremental in building on existing reinforcement learning methods.
The paper tackles the problem of emotional support conversation by formalizing it as a process of positive emotion elicitation, and proposes a reinforcement learning model called Supporter that achieves superior performance in eliciting positive emotions while maintaining conversational coherence.
Emotional support conversation (ESC) aims to provide emotional support (ES) to improve one's mental state. Existing works stay at fitting grounded responses and responding strategies (e.g., question), which ignore the effect on ES and lack explicit goals to guide emotional positive transition. To this end, we introduce a new paradigm to formalize multi-turn ESC as a process of positive emotion elicitation. Addressing this task requires finely adjusting the elicitation intensity in ES as the conversation progresses while maintaining conversational goals like coherence. In this paper, we propose Supporter, a mixture-of-expert-based reinforcement learning model, and well design ES and dialogue coherence rewards to guide policy's learning for responding. Experiments verify the superiority of Supporter in achieving positive emotion elicitation during responding while maintaining conversational goals including coherence.