CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Jie, Zhou, Yuanchen, Jiang, Shuo, Li, Junhui, Guo, Lifan, Chen, Feng, Zhang, Chi, Kong, Fang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914274232762368
author Zhu, Jie
Zhou, Yuanchen
Jiang, Shuo
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
Kong, Fang
author_facet Zhu, Jie
Zhou, Yuanchen
Jiang, Shuo
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
Kong, Fang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
Zhu, Jie
Zhou, Yuanchen
Jiang, Shuo
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
Kong, Fang
Computation and Language
Artificial Intelligence
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.
title CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.05122