<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoehn-etal-2025-speakers">
    <titleInfo>
        <title>On Speakers’ Identities, Autism Self-Disclosures and LLM-Powered Robots</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sviatlana</namePart>
        <namePart type="family">Hoehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fred</namePart>
        <namePart type="family">Philippy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elisabeth</namePart>
        <namePart type="family">Andre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Frédéric</namePart>
            <namePart type="family">Béchet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabrice</namePart>
            <namePart type="family">Lefèvre</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicholas</namePart>
            <namePart type="family">Asher</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Seokhwan</namePart>
            <namePart type="family">Kim</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Teva</namePart>
            <namePart type="family">Merlin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Avignon, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Dialogue agents become more engaging through recipient design, which needs user-specific information. However, a user’s identification with marginalized communities, such as migration or disability background, can elicit biased language. This study compares LLM responses to neurodivergent user personas with disclosed vs. masked neurodivergent identities. A dataset built from public Instagram comments was used to evaluate four open-source models on story generation, dialogue generation, and retrieval-augmented question answering. Our analyses show biases in user’s identity construction across all models and tasks. Binary classifiers trained on each model can distinguish between language generated for prompts with or without self-disclosures, with stronger biases linked to more explicit disclosures. Some models’ safety mechanisms result in denial of service behaviors. LLM’s recipient design to neurodivergent identities relies on stereotypes tied to neurodivergence.</abstract>
    <identifier type="citekey">hoehn-etal-2025-speakers</identifier>
    <location>
        <url>https://aclanthology.org/2025.sigdial-1.40/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>484</start>
            <end>503</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On Speakers’ Identities, Autism Self-Disclosures and LLM-Powered Robots
%A Hoehn, Sviatlana
%A Philippy, Fred
%A Andre, Elisabeth
%Y Béchet, Frédéric
%Y Lefèvre, Fabrice
%Y Asher, Nicholas
%Y Kim, Seokhwan
%Y Merlin, Teva
%S Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2025
%8 August
%I Association for Computational Linguistics
%C Avignon, France
%F hoehn-etal-2025-speakers
%X Dialogue agents become more engaging through recipient design, which needs user-specific information. However, a user’s identification with marginalized communities, such as migration or disability background, can elicit biased language. This study compares LLM responses to neurodivergent user personas with disclosed vs. masked neurodivergent identities. A dataset built from public Instagram comments was used to evaluate four open-source models on story generation, dialogue generation, and retrieval-augmented question answering. Our analyses show biases in user’s identity construction across all models and tasks. Binary classifiers trained on each model can distinguish between language generated for prompts with or without self-disclosures, with stronger biases linked to more explicit disclosures. Some models’ safety mechanisms result in denial of service behaviors. LLM’s recipient design to neurodivergent identities relies on stereotypes tied to neurodivergence.
%U https://aclanthology.org/2025.sigdial-1.40/
%P 484-503

Markdown (Informal)

[On Speakers’ Identities, Autism Self-Disclosures and LLM-Powered Robots](https://aclanthology.org/2025.sigdial-1.40/) (Hoehn et al., SIGDIAL 2025)

• On Speakers’ Identities, Autism Self-Disclosures and LLM-Powered Robots (Hoehn et al., SIGDIAL 2025)

ACL

• Sviatlana Hoehn, Fred Philippy, and Elisabeth Andre. 2025. On Speakers’ Identities, Autism Self-Disclosures and LLM-Powered Robots. In Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 484–503, Avignon, France. Association for Computational Linguistics.