重新思考心理治疗对话生成与动机性访谈策略的对齐
Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies
AI总结：
本研究通过让大语言模型先预测动机性访谈策略再生成对话，探索策略对齐以提升心理治疗对话的可控性与可解释性，实验验证了其有效性。
摘要：
大型语言模型（LLMs）的最新进展在生成心理治疗对话方面展现出潜力，尤其是在动机性访谈（MI）的背景下。然而，鉴于心理治疗的高度敏感性，LLM输出固有的缺乏透明度带来了重大挑战。应用MI策略（一组动机性访谈技能）来生成更具可控性且符合治疗原则、同时具备可解释性的对话，提供了一种可能的解决方案。在本研究中，我们探索LLMs与MI策略的对齐，首先提示LLMs预测合适的策略作为推理依据，然后利用这些策略指导后续的对话生成。我们旨在探究这种对齐是否能带来更具可控性和可解释性的生成结果。我们进行了多项实验，包括自动评估和人工评估，以验证MI策略在对齐心理治疗对话生成方面的有效性。我们的研究结果表明，LLMs在生成策略对齐的对话方面具有潜力，并为心理治疗环境中的实际应用指明了方向。
英文摘要：
Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI). However, the inherent lack of transparency in LLM outputs presents significant challenges given the sensitive nature of psychotherapy. Applying MI strategies, a set of MI skills, to generate more controllable therapeutic-adherent conversations with explainability provides a possible solution. In this work, we explore the alignment of LLMs with MI strategies by first prompting the LLMs to predict the appropriate strategies as reasoning and then utilizing these strategies to guide the subsequent dialogue generation. We seek to investigate whether such alignment leads to more controllable and explainable generations. Multiple experiments including automatic and human evaluations are conducted to validate the effectiveness of MI strategies in aligning psychotherapy dialogue generation. Our findings demonstrate the potential of LLMs in producing strategically aligned dialogues and suggest directions for practical applications in psychotherapeutic settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
