Psych\=eChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
Zhentao Xia, Yongqi Fan, Yuxiang Chu, Yichao Yin, Liangliang Chen, Tong Ruan, Weiyan Zhang

TL;DR
Psych=eChat is a novel framework that enhances psychological counseling with explicit emotion shift tracking and safety risk analysis, improving emotional understanding and safety in LLM-based counseling.
Contribution
It introduces a dual-module system for emotion management and risk control, along with two modeling paradigms for effective emotion and safety-aware counseling.
Findings
Outperforms existing methods in emotional insight
Demonstrates improved safety risk mitigation
Effective in dialogue-level evaluations and human assessments
Abstract
Large language models (LLMs) have demonstrated notable advancements in psychological counseling. However, existing models generally do not explicitly model seekers' emotion shifts across counseling sessions, a core focus in classical psychological schools. Moreover, how to align counselor models' responses with these emotion shifts while proactively mitigating safety risks remains underexplored. To bridge these gaps, we propose Psych\=eChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling. Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module, to capture seekers' current emotions and emotion shifts; and Risk Control Module, to anticipate seekers' subsequent reactions and identify potential risks. Furthermore, we introduce two modeling…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMental Health via Writing · Digital Mental Health Interventions · Emotion and Mood Recognition
