LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation
Yuxuan Li, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Xuetao Wei (ORCID: https://orcid.org/0000-0002-4450-2251)
- Jiashi Gao (ORCID: https://orcid.org/0000-0003-3224-2402)
- Xiangyu Zhao (ORCID: https://orcid.org/0000-0002-2186-476X)
- Xinwei Guo (ORCID: https://orcid.org/0000-0002-8781-3340)
- Haiyan Wu (ORCID: https://orcid.org/0000-0001-5880-3998)
- Xin Yao (ORCID: https://orcid.org/0000-0001-7165-937X)
- Quanying Liu (ORCID: https://orcid.org/0000-0002-2501-7656)
- Yuxuan Li (ORCID: https://orcid.org/0000-0002-9201-6266)
- Jiaxin Zhang (ORCID: https://orcid.org/0000-0002-7576-6110)
- Guanhua Chen (ORCID: https://orcid.org/0000-0002-9314-2037)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.1400
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China