Can LLMs identify and repair ruptures? Comparison between clinician practices and LLM behaviors

2026-09-21

AI Summary

研究通过对比临床医生和大型语言模型在识别与修复心理治疗对话中关系破裂的能力，发现模型依赖显式线索且解决策略较为刻板。

Abstract

Ruptures represent common albeit critical moments in interaction where relational alignment breaks down, making them essential for evaluating AI where trust and engagement matter most. In a scenario-driven empirical study, we examined the performance of three LLMs at identifying and resolving ruptures across 21 mental health conversations and 22 experts' evaluation of the strategies. For identification, LLMs relied on explicit linguistic cues within single turns whereas experts integrated implicit, relational, and contextual information across the conversation. For resolution, LLMs tended to produce more directive and scripted responses whereas experts adopted process-oriented strategies such as validation, open-ended exploration, and psychoeducation. Overall, LLMs showed higher agreement with predefined labels in identification, but not in resolution where experts rated their responses only moderately effective, with consistent limitations in timing, depth, and contextual sensitivity. We discuss implications for the design of mental health conversational agents emphasizing relational awareness, pacing, and human-in-the-loop support.

Problem

• LLMs
• ruptures
• mental health conversations
• relational alignment
• trust and engagement

Innovation

• LLMs
• rupture identification and repair
• mental health conversations
• relational awareness
• human-in-the-loop support