@inproceedings{freizeit-etal-2026-muse,
title = "{M}u{S}e-{MI}: A Framework for Assessing Multi-Session Motivational Interviewing with {AI}-Generated Patients",
author = "Freizeit, Topaz and
Zisquit, Moreah and
Hashiloni, Kai Golan and
Tavens, Chaitze and
Friedman, Doron and
Bar, Kfir",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.25/",
pages = "432--478",
ISBN = "979-8-89176-444-6",
abstract = "Evaluating conversational therapist competence in Motivational Interviewing (MI) requires multi-session assessment, yet current benchmarks rely on simulated patients that fail to model progression from session to session. We present MuSe-MI (Multiple Sessions Motivational Interviewing), a simulated patient framework grounded in Motivational Enhancement Therapy (MET), a multi-session clinical protocol of MI. MuSe-MI regulates dialogue generation through four evolving internal states from the MET clinical manual (anger, readiness to change, problem recognition, and self-efficacy), paired with an inter-session life event simulator and structured memory. Blind evaluations by licensed clinical psychologists confirm that patient dialogue reflects these internal states with high inter-rater agreement. Experiments show that MuSe-MI reliably distinguishes conversational therapist MI adherence levels based on patient language progression, establishing an automated multi-session evaluation benchmark."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="freizeit-etal-2026-muse">
<titleInfo>
<title>MuSe-MI: A Framework for Assessing Multi-Session Motivational Interviewing with AI-Generated Patients</title>
</titleInfo>
<name type="personal">
<namePart type="given">Topaz</namePart>
<namePart type="family">Freizeit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moreah</namePart>
<namePart type="family">Zisquit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="given">Golan</namePart>
<namePart type="family">Hashiloni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaitze</namePart>
<namePart type="family">Tavens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doron</namePart>
<namePart type="family">Friedman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Evaluating conversational therapist competence in Motivational Interviewing (MI) requires multi-session assessment, yet current benchmarks rely on simulated patients that fail to model progression from session to session. We present MuSe-MI (Multiple Sessions Motivational Interviewing), a simulated patient framework grounded in Motivational Enhancement Therapy (MET), a multi-session clinical protocol of MI. MuSe-MI regulates dialogue generation through four evolving internal states from the MET clinical manual (anger, readiness to change, problem recognition, and self-efficacy), paired with an inter-session life event simulator and structured memory. Blind evaluations by licensed clinical psychologists confirm that patient dialogue reflects these internal states with high inter-rater agreement. Experiments show that MuSe-MI reliably distinguishes conversational therapist MI adherence levels based on patient language progression, establishing an automated multi-session evaluation benchmark.</abstract>
<identifier type="citekey">freizeit-etal-2026-muse</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.25/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>432</start>
<end>478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuSe-MI: A Framework for Assessing Multi-Session Motivational Interviewing with AI-Generated Patients
%A Freizeit, Topaz
%A Zisquit, Moreah
%A Hashiloni, Kai Golan
%A Tavens, Chaitze
%A Friedman, Doron
%A Bar, Kfir
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F freizeit-etal-2026-muse
%X Evaluating conversational therapist competence in Motivational Interviewing (MI) requires multi-session assessment, yet current benchmarks rely on simulated patients that fail to model progression from session to session. We present MuSe-MI (Multiple Sessions Motivational Interviewing), a simulated patient framework grounded in Motivational Enhancement Therapy (MET), a multi-session clinical protocol of MI. MuSe-MI regulates dialogue generation through four evolving internal states from the MET clinical manual (anger, readiness to change, problem recognition, and self-efficacy), paired with an inter-session life event simulator and structured memory. Blind evaluations by licensed clinical psychologists confirm that patient dialogue reflects these internal states with high inter-rater agreement. Experiments show that MuSe-MI reliably distinguishes conversational therapist MI adherence levels based on patient language progression, establishing an automated multi-session evaluation benchmark.
%U https://aclanthology.org/2026.findings-aacl.25/
%P 432-478
Markdown (Informal)
[MuSe-MI: A Framework for Assessing Multi-Session Motivational Interviewing with AI-Generated Patients](https://aclanthology.org/2026.findings-aacl.25/) (Freizeit et al., Findings 2026)
ACL