PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915737692536832 |
|---|---|
| author | Xia, Zhentao Fan, Yongqi Chu, Yuxiang Yin, Yichao Chen, Liangliang Ruan, Tong Zhang, Weiyan |
| author_facet | Xia, Zhentao Fan, Yongqi Chu, Yuxiang Yin, Yichao Chen, Liangliang Ruan, Tong Zhang, Weiyan |
| contents | 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 PsychēChat, 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 paradigms. The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline. The LLM Mode integrates these stages into a unified chain-of-thought for end-to-end inference, balancing efficiency and performance. Extensive experiments, including interactive scoring, dialogue-level evaluation, and human assessment, demonstrate that PsychēChat outperforms existing methods for emotional insight and safety control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12392 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling Xia, Zhentao Fan, Yongqi Chu, Yuxiang Yin, Yichao Chen, Liangliang Ruan, Tong Zhang, Weiyan Artificial Intelligence 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 PsychēChat, 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 paradigms. The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline. The LLM Mode integrates these stages into a unified chain-of-thought for end-to-end inference, balancing efficiency and performance. Extensive experiments, including interactive scoring, dialogue-level evaluation, and human assessment, demonstrate that PsychēChat outperforms existing methods for emotional insight and safety control. |
| title | PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.12392 |