STAR: Strategy-Aware Refinement Module in Multitask Learning for Emotional Support Conversations
Year: 2025
Type: conference-paper
Abstract: Effective emotional support in conversation requires strategic decision making, as it involves complex, context-sensitive reasoning tailored to diverse individual needs.The Emotional Support Conversation framework addresses this by organizing interactions into three distinct phases-exploration, comforting, and action-which guide strategy selection during response generation.While multitask learning has been applied to jointly optimize strategy prediction and response generation, it often suffers from task interference due to conflicting learning objectives.To overcome this, we propose the Strategy-Aware Refinement Module (STAR), which disentangles the decoder's hidden states for each task and selectively fuses them via a dynamic gating mechanism.This design preserves task-specific representations while allowing controlled information exchange between tasks, thus reducing interference.Experimental results demonstrate that STAR effectively reduces task interference and achieves state-of-the-art performance in both strategy prediction and supportive response generation.
Authors: Suhyun Lee, Changheon Han, Woohwan Jung, Minsam Ko
Institution: Hanyang University
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412944261