@inproceedings{schuster-etal-2026-whose,
title = "Whose Facts Win? {LLM} Source Preferences under Knowledge Conflicts",
author = "Schuster, Jakob and
Gautam, Vagrant and
Markert, Katja",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1357/",
pages = "29430--29459",
ISBN = "979-8-89176-390-6",
abstract = "As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved information has gone unexamined. We address this gap with a novel framework to investigate how source preferences affect LLM resolution of inter-context knowledge conflicts in English, motivated by interdisciplinary research on credibility. By using synthetic sources, we study preferences for different types of sources without inheriting the biases of specific real-world sources. With a comprehensive, tightly-controlled evaluation of 13 open-weight LLMs, we find that LLMs prefer institutionally-corroborated information (e.g., government or newspaper sources) over information from people and social media. However, these source preferences can be reversed by simply repeating information from less credible sources. To mitigate repetition effects and maintain consistent preferences, we propose a novel method that reduces repetition bias by up to 79.2{\%}, while also maintaining at least 72.5{\%} of original preferences. We release all data and code to encourage future work on credibility and source preferences in knowledge-intensive NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schuster-etal-2026-whose">
<titleInfo>
<title>Whose Facts Win? LLM Source Preferences under Knowledge Conflicts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Schuster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vagrant</namePart>
<namePart type="family">Gautam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katja</namePart>
<namePart type="family">Markert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved information has gone unexamined. We address this gap with a novel framework to investigate how source preferences affect LLM resolution of inter-context knowledge conflicts in English, motivated by interdisciplinary research on credibility. By using synthetic sources, we study preferences for different types of sources without inheriting the biases of specific real-world sources. With a comprehensive, tightly-controlled evaluation of 13 open-weight LLMs, we find that LLMs prefer institutionally-corroborated information (e.g., government or newspaper sources) over information from people and social media. However, these source preferences can be reversed by simply repeating information from less credible sources. To mitigate repetition effects and maintain consistent preferences, we propose a novel method that reduces repetition bias by up to 79.2%, while also maintaining at least 72.5% of original preferences. We release all data and code to encourage future work on credibility and source preferences in knowledge-intensive NLP.</abstract>
<identifier type="citekey">schuster-etal-2026-whose</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1357/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>29430</start>
<end>29459</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whose Facts Win? LLM Source Preferences under Knowledge Conflicts
%A Schuster, Jakob
%A Gautam, Vagrant
%A Markert, Katja
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F schuster-etal-2026-whose
%X As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved information has gone unexamined. We address this gap with a novel framework to investigate how source preferences affect LLM resolution of inter-context knowledge conflicts in English, motivated by interdisciplinary research on credibility. By using synthetic sources, we study preferences for different types of sources without inheriting the biases of specific real-world sources. With a comprehensive, tightly-controlled evaluation of 13 open-weight LLMs, we find that LLMs prefer institutionally-corroborated information (e.g., government or newspaper sources) over information from people and social media. However, these source preferences can be reversed by simply repeating information from less credible sources. To mitigate repetition effects and maintain consistent preferences, we propose a novel method that reduces repetition bias by up to 79.2%, while also maintaining at least 72.5% of original preferences. We release all data and code to encourage future work on credibility and source preferences in knowledge-intensive NLP.
%U https://aclanthology.org/2026.acl-long.1357/
%P 29430-29459
Markdown (Informal)
[Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://aclanthology.org/2026.acl-long.1357/) (Schuster et al., ACL 2026)
ACL
- Jakob Schuster, Vagrant Gautam, and Katja Markert. 2026. Whose Facts Win? LLM Source Preferences under Knowledge Conflicts. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29430–29459, San Diego, California, United States. Association for Computational Linguistics.