Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning
This addresses the challenge of creating effective AI-driven motivational tools for healthcare or coaching, though it appears incremental as it builds on existing large language models with a new learning method.
The paper tackles the problem of building a dialogue system for Motivational Interviewing by learning conversation strategies from expert demonstrations, resulting in improved active listening, reduced unsolicited advice, and more collaborative responses as shown in evaluations.
We consider the task of building a dialogue system that can motivate users to adopt positive lifestyle changes: Motivational Interviewing. Addressing such a task requires a system that can infer \textit{how} to motivate a user effectively. We propose DIIT, a framework that is capable of learning and applying conversation strategies in the form of natural language inductive rules from expert demonstrations. Automatic and human evaluation on instruction-following large language models show natural language strategy descriptions discovered by DIIR can improve active listening skills, reduce unsolicited advice, and promote more collaborative and less authoritative responses, outperforming various demonstration utilization methods.