<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-eeyore">
    <titleInfo>
        <title>Eeyore: Realistic Depression Simulation via Expert-in-the-Loop Supervised and Preference Optimization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Siyang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bianca</namePart>
        <namePart type="family">Brie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenda</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laura</namePart>
        <namePart type="family">Biester</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Pennebaker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rada</namePart>
        <namePart type="family">Mihalcea</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) have been previously explored for mental healthcare training and therapy client simulation, but they still fall short in authentically capturing diverse client traits and psychological conditions. We introduce Eeyore , an 8B model optimized for realistic depression simulation through a structured alignment framework, incorporating expert input at every stage.First, we systematically curate real-world depression-related conversations, extracting depressive traits to guide data filtering and psychological profile construction, and use this dataset to instruction-tune Eeyore for profile adherence. Next, to further enhance realism, Eeyore undergoes iterative preference optimization—first leveraging model-generated preferences and then calibrating with a small set of expert-annotated preferences.Throughout the entire pipeline, we actively collaborate with domain experts, developing interactive interfaces to validate trait extraction and iteratively refine structured psychological profiles for clinically meaningful role-play customization.Despite its smaller model size, the Eeyore depression simulation outperforms GPT-4o with SOTA prompting strategies, both in linguistic authenticity and profile adherence.</abstract>
    <identifier type="citekey">liu-etal-2025-eeyore</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.707</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.707/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>13750</start>
            <end>13770</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Eeyore: Realistic Depression Simulation via Expert-in-the-Loop Supervised and Preference Optimization
%A Liu, Siyang
%A Brie, Bianca
%A Li, Wenda
%A Biester, Laura
%A Lee, Andrew
%A Pennebaker, James
%A Mihalcea, Rada
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F liu-etal-2025-eeyore
%X Large Language Models (LLMs) have been previously explored for mental healthcare training and therapy client simulation, but they still fall short in authentically capturing diverse client traits and psychological conditions. We introduce Eeyore , an 8B model optimized for realistic depression simulation through a structured alignment framework, incorporating expert input at every stage.First, we systematically curate real-world depression-related conversations, extracting depressive traits to guide data filtering and psychological profile construction, and use this dataset to instruction-tune Eeyore for profile adherence. Next, to further enhance realism, Eeyore undergoes iterative preference optimization—first leveraging model-generated preferences and then calibrating with a small set of expert-annotated preferences.Throughout the entire pipeline, we actively collaborate with domain experts, developing interactive interfaces to validate trait extraction and iteratively refine structured psychological profiles for clinically meaningful role-play customization.Despite its smaller model size, the Eeyore depression simulation outperforms GPT-4o with SOTA prompting strategies, both in linguistic authenticity and profile adherence.
%R 10.18653/v1/2025.findings-acl.707
%U https://aclanthology.org/2025.findings-acl.707/
%U https://doi.org/10.18653/v1/2025.findings-acl.707
%P 13750-13770

Markdown (Informal)

[Eeyore: Realistic Depression Simulation via Expert-in-the-Loop Supervised and Preference Optimization](https://aclanthology.org/2025.findings-acl.707/) (Liu et al., Findings 2025)

• Eeyore: Realistic Depression Simulation via Expert-in-the-Loop Supervised and Preference Optimization (Liu et al., Findings 2025)

ACL

• Siyang Liu, Bianca Brie, Wenda Li, Laura Biester, Andrew Lee, James Pennebaker, and Rada Mihalcea. 2025. Eeyore: Realistic Depression Simulation via Expert-in-the-Loop Supervised and Preference Optimization. In Findings of the Association for Computational Linguistics: ACL 2025, pages 13750–13770, Vienna, Austria. Association for Computational Linguistics.