<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-sweet">
    <titleInfo>
        <title>Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Helena</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Edric</namePart>
        <namePart type="given">Castel</namePart>
        <namePart type="given">C</namePart>
        <namePart type="family">Hao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karl</namePart>
        <namePart type="family">Bautista</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Francis</namePart>
        <namePart type="given">Gabriel</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Magleo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Renzo</namePart>
        <namePart type="family">Panti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danielle</namePart>
        <namePart type="given">Beatrice</namePart>
        <namePart type="given">Ledesma</namePart>
        <namePart type="family">Olalia</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>Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Rui</namePart>
            <namePart type="family">Sousa-Silva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henrique</namePart>
            <namePart type="family">Lopes Cardoso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maarit</namePart>
            <namePart type="family">Koponen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Pareja-Lora</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">979-8-89176-471-2</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are increasingly used for emotional support and relationship advice, where a model’s tendency to preserve a user’s face can inadvertently reinforce harmful interpersonal behaviors. To systematically examine this risk, we developed the Romantic Relationship Advice-Seeking Prompts (RRASP) dataset of 2,400 prompts across five relationship themes and evaluated social sycophancy using the ELEPHANT framework on two consumer-facing models, GPT-5 Mini and Gemini 3 Flash. Contrary to our initial hypothesis, grammatical mood alone did not produce systematic differences in sycophantic behavior, suggesting that what a user implies matters more than how they phrase it. Instead, perspective-driven framing had a stronger influence, with gaps between original and flipped prompts widening in follow-up responses. Consistent increases in framing and moral sycophancy across turns indicate that models become more likely to accept a user’s stated premises and affirm their ethical stance as a dialogue progresses. Notably, Gemini 3 Flash exhibited substantially smaller increases in moral sycophancy than GPT-5 Mini, suggesting it is more resistant to reinforcing ethically problematic positions across turns.</abstract>
    <identifier type="citekey">choi-etal-2026-sweet</identifier>
    <location>
        <url>https://aclanthology.org/2026.luhme-1.21/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>272</start>
            <end>285</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice
%A Choi, Helena
%A Hao, Edric Castel C.
%A Bautista, Karl
%A Magleo, Francis Gabriel A.
%A Panti, Renzo
%A Olalia, Danielle Beatrice Ledesma
%Y Sousa-Silva, Rui
%Y Lopes Cardoso, Henrique
%Y Koponen, Maarit
%Y Pareja-Lora, Antonio
%S Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-471-2
%F choi-etal-2026-sweet
%X Large language models (LLMs) are increasingly used for emotional support and relationship advice, where a model’s tendency to preserve a user’s face can inadvertently reinforce harmful interpersonal behaviors. To systematically examine this risk, we developed the Romantic Relationship Advice-Seeking Prompts (RRASP) dataset of 2,400 prompts across five relationship themes and evaluated social sycophancy using the ELEPHANT framework on two consumer-facing models, GPT-5 Mini and Gemini 3 Flash. Contrary to our initial hypothesis, grammatical mood alone did not produce systematic differences in sycophantic behavior, suggesting that what a user implies matters more than how they phrase it. Instead, perspective-driven framing had a stronger influence, with gaps between original and flipped prompts widening in follow-up responses. Consistent increases in framing and moral sycophancy across turns indicate that models become more likely to accept a user’s stated premises and affirm their ethical stance as a dialogue progresses. Notably, Gemini 3 Flash exhibited substantially smaller increases in moral sycophancy than GPT-5 Mini, suggesting it is more resistant to reinforcing ethically problematic positions across turns.
%U https://aclanthology.org/2026.luhme-1.21/
%P 272-285

Markdown (Informal)

[Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice](https://aclanthology.org/2026.luhme-1.21/) (Choi et al., LUHME 2026)

• Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice (Choi et al., LUHME 2026)

ACL

• Helena Choi, Edric Castel C. Hao, Karl Bautista, Francis Gabriel A. Magleo, Renzo Panti, and Danielle Beatrice Ledesma Olalia. 2026. Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice. In Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026), pages 272–285, Budapest, Hungary. Association for Computational Linguistics.