@inproceedings{basar-etal-2025-well,
title = "How Well Can Large Language Models Reflect? A Human Evaluation of {LLM}-generated Reflections for Motivational Interviewing Dialogues",
author = "Basar, Erkan and
Sun, Xin and
Hendrickx, Iris and
de Wit, Jan and
Bosse, Tibor and
De Bruijn, Gert-Jan and
Bosch, Jos A. and
Krahmer, Emiel",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.135/",
pages = "1964--1982",
abstract = "Motivational Interviewing (MI) is a counseling technique that promotes behavioral change through reflective responses to mirror or refine client statements. While advanced Large Language Models (LLMs) can generate engaging dialogues, challenges remain for applying them in a sensitive context such as MI. This work assesses the potential of LLMs to generate MI reflections via three LLMs: GPT-4, Llama-2, and BLOOM, and explores the effect of dialogue context size and integration of MI strategies for reflection generation by LLMs. We conduct evaluations using both automatic metrics and human judges on four criteria: appropriateness, relevance, engagement, and naturalness, to assess whether these LLMs can accurately generate the nuanced therapeutic communication required in MI. While we demonstrate LLMs' potential in generating MI reflections comparable to human therapists, content analysis shows that significant challenges remain. By identifying the strengths and limitations of LLMs in generating empathetic and contextually appropriate reflections in MI, this work contributes to the ongoing dialogue in enhancing LLM`s role in therapeutic counseling."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basar-etal-2025-well">
<titleInfo>
<title>How Well Can Large Language Models Reflect? A Human Evaluation of LLM-generated Reflections for Motivational Interviewing Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erkan</namePart>
<namePart type="family">Basar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Hendrickx</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">de Wit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tibor</namePart>
<namePart type="family">Bosse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gert-Jan</namePart>
<namePart type="family">De Bruijn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jos</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Bosch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">Krahmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Motivational Interviewing (MI) is a counseling technique that promotes behavioral change through reflective responses to mirror or refine client statements. While advanced Large Language Models (LLMs) can generate engaging dialogues, challenges remain for applying them in a sensitive context such as MI. This work assesses the potential of LLMs to generate MI reflections via three LLMs: GPT-4, Llama-2, and BLOOM, and explores the effect of dialogue context size and integration of MI strategies for reflection generation by LLMs. We conduct evaluations using both automatic metrics and human judges on four criteria: appropriateness, relevance, engagement, and naturalness, to assess whether these LLMs can accurately generate the nuanced therapeutic communication required in MI. While we demonstrate LLMs’ potential in generating MI reflections comparable to human therapists, content analysis shows that significant challenges remain. By identifying the strengths and limitations of LLMs in generating empathetic and contextually appropriate reflections in MI, this work contributes to the ongoing dialogue in enhancing LLM‘s role in therapeutic counseling.</abstract>
<identifier type="citekey">basar-etal-2025-well</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.135/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>1964</start>
<end>1982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Well Can Large Language Models Reflect? A Human Evaluation of LLM-generated Reflections for Motivational Interviewing Dialogues
%A Basar, Erkan
%A Sun, Xin
%A Hendrickx, Iris
%A de Wit, Jan
%A Bosse, Tibor
%A De Bruijn, Gert-Jan
%A Bosch, Jos A.
%A Krahmer, Emiel
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F basar-etal-2025-well
%X Motivational Interviewing (MI) is a counseling technique that promotes behavioral change through reflective responses to mirror or refine client statements. While advanced Large Language Models (LLMs) can generate engaging dialogues, challenges remain for applying them in a sensitive context such as MI. This work assesses the potential of LLMs to generate MI reflections via three LLMs: GPT-4, Llama-2, and BLOOM, and explores the effect of dialogue context size and integration of MI strategies for reflection generation by LLMs. We conduct evaluations using both automatic metrics and human judges on four criteria: appropriateness, relevance, engagement, and naturalness, to assess whether these LLMs can accurately generate the nuanced therapeutic communication required in MI. While we demonstrate LLMs’ potential in generating MI reflections comparable to human therapists, content analysis shows that significant challenges remain. By identifying the strengths and limitations of LLMs in generating empathetic and contextually appropriate reflections in MI, this work contributes to the ongoing dialogue in enhancing LLM‘s role in therapeutic counseling.
%U https://aclanthology.org/2025.coling-main.135/
%P 1964-1982
Markdown (Informal)
[How Well Can Large Language Models Reflect? A Human Evaluation of LLM-generated Reflections for Motivational Interviewing Dialogues](https://aclanthology.org/2025.coling-main.135/) (Basar et al., COLING 2025)
ACL
- Erkan Basar, Xin Sun, Iris Hendrickx, Jan de Wit, Tibor Bosse, Gert-Jan De Bruijn, Jos A. Bosch, and Emiel Krahmer. 2025. How Well Can Large Language Models Reflect? A Human Evaluation of LLM-generated Reflections for Motivational Interviewing Dialogues. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1964–1982, Abu Dhabi, UAE. Association for Computational Linguistics.