CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
This work addresses the need for more empathetic and cognitively robust emotional support systems, representing an incremental advancement by focusing on reasoning without synthetic data.
The paper tackles the problem of enhancing cognitive reasoning in Emotional Support Conversation (ESC) by proposing the CARE framework, which uses the original training set and reinforcement learning to generate logically coherent and supportive responses, resulting in significant improvements in both logical soundness and supportive quality.
Emotional Support Conversation (ESC) plays a vital role in alleviating psychological stress and providing emotional value through dialogue. While recent studies have largely focused on data augmentation and synthetic corpus construction, they often overlook the deeper cognitive reasoning processes that underpin effective emotional support. To address this gap, we propose \textbf{CARE}, a novel framework that strengthens reasoning in ESC without relying on large-scale synthetic data. CARE leverages the original ESC training set to guide models in generating logically coherent and supportive responses, thereby explicitly enhancing cognitive reasoning. Building on this foundation, we further employ reinforcement learning to refine and reinforce the reasoning process. Experimental results demonstrate that CARE significantly improves both the logical soundness and supportive quality of responses, advancing the development of empathetic, cognitively robust, and human-like emotional support systems.