<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chandra-etal-2026-reasoning">
    <titleInfo>
        <title>Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohit</namePart>
        <namePart type="family">Chandra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Siddharth</namePart>
        <namePart type="family">Sriraman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Harneet</namePart>
        <namePart type="given">Singh</namePart>
        <namePart type="family">Khanuja</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiqiao</namePart>
        <namePart type="family">Jin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Munmun</namePart>
        <namePart type="family">De Choudhury</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Limited access to mental healthcare, extended wait times, and increasing capabilities of Large Language Models (LLMs) has led individuals to turn to LLMs for fulfilling their mental health needs. However, examining the multi-turn mental health conversation capabilities of LLMs remains under-explored. Existing evaluation frameworks typically focus on diagnostic accuracy and win-rates and often overlook alignment with patient-specific goals, values, and personalities required for meaningful conversations. To address this, we introduce MedAgent, a novel framework for synthetically generating realistic, multi-turn mental health sensemaking conversations and use it to create the Mental Health Sensemaking Dialogue (MHSD) dataset, comprising over 2,200 patient–LLM conversations. Additionally, we present MultiSenseEval, a holistic framework to evaluate the multi-turn conversation abilities of LLMs in healthcare settings using human-centric criteria. Our findings reveal that frontier reasoning models yield below-par performance for patient-centric communication and struggle at precise (”hard”) diagnostic capabilities with average accuracy of ~31%. Additionally, we observed variation in model performance based on patient’s persona and performance drop with increasing turns in the conversation. Our work provides a comprehensive synthetic data generation framework, a dataset and evaluation framework for assessing LLMs in multi-turn mental health conversations.</abstract>
    <identifier type="citekey">chandra-etal-2026-reasoning</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.2164/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>46648</start>
            <end>46682</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations
%A Chandra, Mohit
%A Sriraman, Siddharth
%A Khanuja, Harneet Singh
%A Jin, Yiqiao
%A De Choudhury, Munmun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F chandra-etal-2026-reasoning
%X Limited access to mental healthcare, extended wait times, and increasing capabilities of Large Language Models (LLMs) has led individuals to turn to LLMs for fulfilling their mental health needs. However, examining the multi-turn mental health conversation capabilities of LLMs remains under-explored. Existing evaluation frameworks typically focus on diagnostic accuracy and win-rates and often overlook alignment with patient-specific goals, values, and personalities required for meaningful conversations. To address this, we introduce MedAgent, a novel framework for synthetically generating realistic, multi-turn mental health sensemaking conversations and use it to create the Mental Health Sensemaking Dialogue (MHSD) dataset, comprising over 2,200 patient–LLM conversations. Additionally, we present MultiSenseEval, a holistic framework to evaluate the multi-turn conversation abilities of LLMs in healthcare settings using human-centric criteria. Our findings reveal that frontier reasoning models yield below-par performance for patient-centric communication and struggle at precise (”hard”) diagnostic capabilities with average accuracy of ~31%. Additionally, we observed variation in model performance based on patient’s persona and performance drop with increasing turns in the conversation. Our work provides a comprehensive synthetic data generation framework, a dataset and evaluation framework for assessing LLMs in multi-turn mental health conversations.
%U https://aclanthology.org/2026.acl-long.2164/
%P 46648-46682

Markdown (Informal)

[Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations](https://aclanthology.org/2026.acl-long.2164/) (Chandra et al., ACL 2026)

• Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations (Chandra et al., ACL 2026)

ACL

• Mohit Chandra, Siddharth Sriraman, Harneet Singh Khanuja, Yiqiao Jin, and Munmun De Choudhury. 2026. Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 46648–46682, San Diego, California, United States. Association for Computational Linguistics.