@inproceedings{li-etal-2025-llms-trust,
title = "{LLM}s Trust Humans More, That{'}s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation",
author = "Li, Yuxuan and
Guo, Xinwei and
Gao, Jiashi and
Chen, Guanhua and
Zhao, Xiangyu and
Zhang, Jiaxin and
Liu, Quanying and
Wu, Haiyan and
Yao, Xin and
Wei, Xuetao",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1400/",
doi = "10.18653/v1/2025.acl-long.1400",
pages = "28844--28858",
ISBN = "979-8-89176-251-0",
abstract = "Retrieval-Augmented Generation (RAG) has been proven to be an effective approach to address the hallucination problem in large language models (LLMs). In current RAG systems, LLMs typically need to synthesize knowledge provided by two main external sources (user prompts and an external database) to generate a final answer. When the knowledge provided by the user conflicts with that retrieved from the database, a critical question arises: Does the LLM favor one knowledge source over the other when generating the answer? In this paper, we are the first to unveil a new phenomenon, Authority Bias, where the LLMs tend to favor the knowledge provided by the user even when it deviates from the facts; this new phenomenon is rigorously evidenced via our novel and comprehensive characterization of Authority Bias in six widely used LLMs and across diverse task scenarios. We propose a novel dataset specifically designed for detecting Authority Bias, called the Authority Bias Detection Dataset (ABDD), and introduce new, detailed metrics to measure Authority Bias. To mitigate Authority bias, we finally propose the Conflict Detection Enhanced Query (CDEQ) framework. We identify the sentences and atomic information that generate conflicts, perform a credibility assessment on the conflicting paragraphs, and ultimately enhance the query to detect perturbed text, thereby reducing Authority bias. Comparative experiments with widely used mitigation methods demonstrate that CDEQ exhibits both effectiveness and advancement, significantly enhancing the robustness of RAG systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-llms-trust">
<titleInfo>
<title>LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinwei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiashi</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quanying</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuetao</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) has been proven to be an effective approach to address the hallucination problem in large language models (LLMs). In current RAG systems, LLMs typically need to synthesize knowledge provided by two main external sources (user prompts and an external database) to generate a final answer. When the knowledge provided by the user conflicts with that retrieved from the database, a critical question arises: Does the LLM favor one knowledge source over the other when generating the answer? In this paper, we are the first to unveil a new phenomenon, Authority Bias, where the LLMs tend to favor the knowledge provided by the user even when it deviates from the facts; this new phenomenon is rigorously evidenced via our novel and comprehensive characterization of Authority Bias in six widely used LLMs and across diverse task scenarios. We propose a novel dataset specifically designed for detecting Authority Bias, called the Authority Bias Detection Dataset (ABDD), and introduce new, detailed metrics to measure Authority Bias. To mitigate Authority bias, we finally propose the Conflict Detection Enhanced Query (CDEQ) framework. We identify the sentences and atomic information that generate conflicts, perform a credibility assessment on the conflicting paragraphs, and ultimately enhance the query to detect perturbed text, thereby reducing Authority bias. Comparative experiments with widely used mitigation methods demonstrate that CDEQ exhibits both effectiveness and advancement, significantly enhancing the robustness of RAG systems.</abstract>
<identifier type="citekey">li-etal-2025-llms-trust</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1400</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1400/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>28844</start>
<end>28858</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation
%A Li, Yuxuan
%A Guo, Xinwei
%A Gao, Jiashi
%A Chen, Guanhua
%A Zhao, Xiangyu
%A Zhang, Jiaxin
%A Liu, Quanying
%A Wu, Haiyan
%A Yao, Xin
%A Wei, Xuetao
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F li-etal-2025-llms-trust
%X Retrieval-Augmented Generation (RAG) has been proven to be an effective approach to address the hallucination problem in large language models (LLMs). In current RAG systems, LLMs typically need to synthesize knowledge provided by two main external sources (user prompts and an external database) to generate a final answer. When the knowledge provided by the user conflicts with that retrieved from the database, a critical question arises: Does the LLM favor one knowledge source over the other when generating the answer? In this paper, we are the first to unveil a new phenomenon, Authority Bias, where the LLMs tend to favor the knowledge provided by the user even when it deviates from the facts; this new phenomenon is rigorously evidenced via our novel and comprehensive characterization of Authority Bias in six widely used LLMs and across diverse task scenarios. We propose a novel dataset specifically designed for detecting Authority Bias, called the Authority Bias Detection Dataset (ABDD), and introduce new, detailed metrics to measure Authority Bias. To mitigate Authority bias, we finally propose the Conflict Detection Enhanced Query (CDEQ) framework. We identify the sentences and atomic information that generate conflicts, perform a credibility assessment on the conflicting paragraphs, and ultimately enhance the query to detect perturbed text, thereby reducing Authority bias. Comparative experiments with widely used mitigation methods demonstrate that CDEQ exhibits both effectiveness and advancement, significantly enhancing the robustness of RAG systems.
%R 10.18653/v1/2025.acl-long.1400
%U https://aclanthology.org/2025.acl-long.1400/
%U https://doi.org/10.18653/v1/2025.acl-long.1400
%P 28844-28858
Markdown (Informal)
[LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation](https://aclanthology.org/2025.acl-long.1400/) (Li et al., ACL 2025)
ACL
- Yuxuan Li, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, and Xuetao Wei. 2025. LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 28844–28858, Vienna, Austria. Association for Computational Linguistics.