EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation

2026-07-26

AI Summary

This work addresses the limitations of existing psychological support dialogue generation methods, which struggle to model the dynamic emotional states of distressed help-seekers and lack empathy-centered emotional interaction. To overcome these challenges, the authors propose a multi-turn dialogue generation framework centered on the help-seeker’s emotional trajectory. The framework introduces, for the first time, an emotion trajectory control mechanism and an activation-gated emotional schema module, integrated with cognitive profiling and large language models to jointly generate help-seeker utterances with hierarchical emotional expression and counselor responses with precise empathy. Experimental results demonstrate that the proposed approach significantly outperforms current methods in both emotional richness and empathic quality, effectively enhancing the model’s capacity to respond appropriately in emotionally volatile scenarios.

Abstract

Using large language models (LLMs) to assist psychological counseling is an important task in the field of natural language processing. The construction of high-quality psychological support dialogue corpora serves as a critical foundation for training counseling-oriented conversational models. However, existing data generation approaches generally suffer from several limitations, including emotionally stable seekers, limited variation in emotional dynamics, and a high degree of compliance with counselors' guidance. These issues result in LLM that lack the capability to effectively respond to emotionally unstable scenarios. In addition, counselor responses are typically driven by problem-solving objectives, thereby overlooking the role of emotion-focused interaction, which are essential in psychological counseling. To address these gaps, we propose EmoTrace, a multi-turn dialogue corpus generation framework centered on modeling seekers' emotional trajectories. we construct seekers' cognitive profile and introduce a seeker module with emotional schemas and an associated activation mechanism, a counselor module, and an emotional trajectory control module, thereby enhancing the layering of the seeker's emotional expression and the counselor's targeted empathic expression. Experimental results demonstrate that the proposed method outperforms existing approaches in terms of emotional richness and empathy quality.

Problem

• psychological support dialogue
• emotion trajectory
• empathic response
• dialogue generation
• emotional dynamics

Innovation

• emotion trajectory
• empathic dialogue generation
• cognitive profile
• emotional schema
• psychological support corpus