<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lei-etal-2026-truth">
    <titleInfo>
        <title>Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shijun</namePart>
        <namePart type="family">Lei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunji</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haowen</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiwen</namePart>
        <namePart type="family">Yu</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 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>In-group favoritism refers to the phenomenon of favoring members of one’s in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently, in-group favoritism biases have also been identified in generative language models. However, whether persona agents exhibit in-group favoritism when faced with conflicting information, including misinformation, and how to mitigate its adverse effects remain understudied. To address these problems, we propose a Truth or Tribe simulation framework to study agent cooperation in the spread of conflicting information through a triadic interaction paradigm, and conduct controlled trials to evaluate the primary moderating factors. Extensive results showcase that persona agents display strong in-group favoritism, accepting incorrect answers from identity-similar peers at much higher rates than from dissimilar peers. In-group favoritism continues to emerge in defeasible reasoning contexts where no absolute truth exists, and it intensifies as cognitive complexity increases. Furthermore, three intervention strategies—Identity-Blind Instruction, Structured Counterfactual Reasoning, and Heterogeneous Perspective Ensemble—are proposed to mitigate in-group favoritism.</abstract>
    <identifier type="citekey">lei-etal-2026-truth</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.505/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>11596</start>
            <end>11617</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
%A Lei, Shijun
%A Wang, Hongyu
%A Liang, Yunji
%A Zheng, Haowen
%A Guo, Bin
%A Yu, Zhiwen
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F lei-etal-2026-truth
%X In-group favoritism refers to the phenomenon of favoring members of one’s in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently, in-group favoritism biases have also been identified in generative language models. However, whether persona agents exhibit in-group favoritism when faced with conflicting information, including misinformation, and how to mitigate its adverse effects remain understudied. To address these problems, we propose a Truth or Tribe simulation framework to study agent cooperation in the spread of conflicting information through a triadic interaction paradigm, and conduct controlled trials to evaluate the primary moderating factors. Extensive results showcase that persona agents display strong in-group favoritism, accepting incorrect answers from identity-similar peers at much higher rates than from dissimilar peers. In-group favoritism continues to emerge in defeasible reasoning contexts where no absolute truth exists, and it intensifies as cognitive complexity increases. Furthermore, three intervention strategies—Identity-Blind Instruction, Structured Counterfactual Reasoning, and Heterogeneous Perspective Ensemble—are proposed to mitigate in-group favoritism.
%U https://aclanthology.org/2026.emnlp-main.505/
%P 11596-11617

Markdown (Informal)

[Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents](https://aclanthology.org/2026.emnlp-main.505/) (Lei et al., EMNLP 2026)

• Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents (Lei et al., EMNLP 2026)

ACL

• Shijun Lei, Hongyu Wang, Yunji Liang, Haowen Zheng, Bin Guo, and Zhiwen Yu. 2026. Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 11596–11617, Budapest, Hungary. Association for Computational Linguistics.