Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Xin, Tang, Xiao, Ali, Abdallah El, Li, Zhuying, Ren, Pengjie, de Wit, Jan, Pei, Jiahuan, Bosch, Jos A.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2408.06527
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910748566880256
author Sun, Xin
Tang, Xiao
Ali, Abdallah El
Li, Zhuying
Ren, Pengjie
de Wit, Jan
Pei, Jiahuan
Bosch, Jos A.
author_facet Sun, Xin
Tang, Xiao
Ali, Abdallah El
Li, Zhuying
Ren, Pengjie
de Wit, Jan
Pei, Jiahuan
Bosch, Jos A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06527
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies
Sun, Xin
Tang, Xiao
Ali, Abdallah El
Li, Zhuying
Ren, Pengjie
de Wit, Jan
Pei, Jiahuan
Bosch, Jos A.
Computation and Language
Artificial Intelligence
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.
title Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2408.06527