Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning
Computation and Language
2024-03-26 v1
Abstract
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.
Cite
@article{arxiv.2403.15737,
title = {Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning},
author = {Zhouhang Xie and Bodhisattwa Prasad Majumder and Mengjie Zhao and Yoshinori Maeda and Keiichi Yamada and Hiromi Wakaki and Julian McAuley},
journal= {arXiv preprint arXiv:2403.15737},
year = {2024}
}