5 papers
Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning
Jing Ye, Xinpei Zhao, Lu Xiang +2
While current emotional support dialogue systems typically rely on expert-defined scalar rewards for alignment, these signals suffer from severe information sparsity. They cannot e…
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity
Feiteng Fang, Dingwei Chen, Xiang Huang +10
Currently, most reinforcement learning tasks focus on domains like mathematics and programming, where verification is relatively straightforward. However, in subjective tasks such…
EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World
Jing Ye, Lu Xiang, Yaping Zhang +1
Current evaluation paradigms for emotional support conversations tend to reward generic empathetic responses, yet they fail to assess whether the support is genuinely personalized…
From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment
Jing Ye, Lu Xiang, Yaping Zhang +1
Effective emotional support hinges on understanding users' emotions and needs to provide meaningful comfort during multi-turn interactions. Large Language Models (LLMs) show great…
SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent
Jing Ye, Lu Xiang, Yaping Zhang +1
Large Language Models (LLMs) have demonstrated promising potential in providing empathetic support during interactions. However, their responses often become verbose or overly form…