Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914726129172480 |
|---|---|
| author | Xie, Zhouhang Majumder, Bodhisattwa Prasad Zhao, Mengjie Maeda, Yoshinori Yamada, Keiichi Wakaki, Hiromi McAuley, Julian |
| author_facet | Xie, Zhouhang Majumder, Bodhisattwa Prasad Zhao, Mengjie Maeda, Yoshinori Yamada, Keiichi Wakaki, Hiromi McAuley, Julian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15737 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning Xie, Zhouhang Majumder, Bodhisattwa Prasad Zhao, Mengjie Maeda, Yoshinori Yamada, Keiichi Wakaki, Hiromi McAuley, Julian Computation and Language 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. |
| title | Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.15737 |