<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2026-symptoms">
    <titleInfo>
        <title>Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Migyeong</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sihyeon</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minseok</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jisun</namePart>
        <namePart type="family">An</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haewoon</namePart>
        <namePart type="family">Kwak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinyoung</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>While prior studies have shown that gendered stereotypes can influence LLMs’ outputs, little attention has been paid to how gendered cues affect depression severity assessment in mental health contexts. In this paper, we systematically investigate the impact of gendered cues on LLM-based depression severity prediction, focusing on depressive disorder. To this end, we introduce a counterfactual evaluation framework, where we inject two types of gendered cues, explicit and implicit, into social media posts and analyze how they shift LLMs’ severity predictions. Our results reveal that gendered cues systematically shift LLMs’ severity predictions, increasing the risk of underestimating severe cases that may involve suicidal ideation or self-harm. To explore a possible mitigation direction, we propose FairDep, a symptom-grounded reasoning scaffold designed to reduce LLM sensitivity to gendered cues in depression severity prediction. By guiding models to focus on symptom-level evidence, FairDep improves prediction consistency under gender cue perturbations while preserving sensitivity to severe cases. Our findings show that gender cue sensitivity is not merely a fairness concern, but a safety concern in LLM-based mental health assessment, where even small prediction shifts can reduce sensitivity to severe cases involving suicidal ideation or self-harm. Our code and resources are publicly available.</abstract>
    <identifier type="citekey">kang-etal-2026-symptoms</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1031/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>21783</start>
            <end>21800</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment
%A Kang, Migyeong
%A Yang, Sihyeon
%A Kim, Minseok
%A An, Jisun
%A Kwak, Haewoon
%A Han, Jinyoung
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kang-etal-2026-symptoms
%X While prior studies have shown that gendered stereotypes can influence LLMs’ outputs, little attention has been paid to how gendered cues affect depression severity assessment in mental health contexts. In this paper, we systematically investigate the impact of gendered cues on LLM-based depression severity prediction, focusing on depressive disorder. To this end, we introduce a counterfactual evaluation framework, where we inject two types of gendered cues, explicit and implicit, into social media posts and analyze how they shift LLMs’ severity predictions. Our results reveal that gendered cues systematically shift LLMs’ severity predictions, increasing the risk of underestimating severe cases that may involve suicidal ideation or self-harm. To explore a possible mitigation direction, we propose FairDep, a symptom-grounded reasoning scaffold designed to reduce LLM sensitivity to gendered cues in depression severity prediction. By guiding models to focus on symptom-level evidence, FairDep improves prediction consistency under gender cue perturbations while preserving sensitivity to severe cases. Our findings show that gender cue sensitivity is not merely a fairness concern, but a safety concern in LLM-based mental health assessment, where even small prediction shifts can reduce sensitivity to severe cases involving suicidal ideation or self-harm. Our code and resources are publicly available.
%U https://aclanthology.org/2026.findings-emnlp.1031/
%P 21783-21800

Markdown (Informal)

[Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment](https://aclanthology.org/2026.findings-emnlp.1031/) (Kang et al., Findings 2026)

• Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment (Kang et al., Findings 2026)

ACL

• Migyeong Kang, Sihyeon Yang, Minseok Kim, Jisun An, Haewoon Kwak, and Jinyoung Han. 2026. Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 21783–21800, Budapest, Hungary. Association for Computational Linguistics.