Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapy
This addresses the challenge of creating flexible yet controllable AI chatbots for psychotherapy, reducing expert effort and potentially expanding access to mental health support.
The researchers tackled the problem of making large language models (LLMs) more controllable and effective for psychotherapy chatbots by aligning them with expert-crafted dialogue scripts, resulting in aligned LLMs significantly outperforming rule-based and pure LLM chatbots in empathy, dialogue relevance, and therapeutic adherence, and their proposed SSAG method achieved comparable therapeutic effectiveness while requiring less than 40% of expert-crafted content.
Chatbots or conversational agents (CAs) are increasingly used to improve access to digital psychotherapy. Many current systems rely on rigid, rule-based designs, heavily dependent on expert-crafted dialogue scripts for guiding therapeutic conversations. Although advances in large language models (LLMs) offer potential for more flexible interactions, their lack of controllability and explanability poses challenges in high-stakes contexts like psychotherapy. To address this, we conducted two studies in this work to explore how aligning LLMs with expert-crafted scripts can enhance psychotherapeutic chatbot performance. In Study 1 (N=43), an online experiment with a within-subjects design, we compared rule-based, pure LLM, and LLMs aligned with expert-crafted scripts via fine-tuning and prompting. Results showed that aligned LLMs significantly outperformed the other types of chatbots in empathy, dialogue relevance, and adherence to therapeutic principles. Building on findings, we proposed ``Script-Strategy Aligned Generation (SSAG)'', a more flexible alignment approach that reduces reliance on fully scripted content while maintaining LLMs' therapeutic adherence and controllability. In a 10-day field Study 2 (N=21), SSAG achieved comparable therapeutic effectiveness to full-scripted LLMs while requiring less than 40\% of expert-crafted dialogue content. Beyond these results, this work advances LLM applications in psychotherapy by providing a controllable and scalable solution, reducing reliance on expert effort. By enabling domain experts to align LLMs through high-level strategies rather than full scripts, SSAG supports more efficient co-development and expands access to a broader context of psychotherapy.