Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2025

Abstract

Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either ignore the retrieved context or inconsistently blend it with the LLM’s parametric knowledge. This issue is particularly severe in cases of knowledge conflict, where the retrieved context conflicts with the model’s parametric knowledge. While existing faithful RAG approaches enforce strict context adherence through well-designed prompts or modified decoding strategies, our analysis reveals a critical limitation: they achieve faithfulness by forcibly suppressing the model’s parametric knowledge, which undermines the model’s internal knowledge structure and increases the risk of misinterpreting the context. To this end, this paper proposes FaithfulRAG, a novel framework that resolves knowledge conflicts by explicitly modeling discrepancies between the model’s parametric knowledge and retrieved context. Specifically, FaithfulRAG identifies conflicting knowledge at the fact level and designs a self-thinking process, allowing LLMs to reason about and integrate conflicting facts before generating responses. Extensive experiments demonstrate that our method outperforms state-of-the-art methods. The code is available at https://github.com/DeepLearnXMU/Faithful-RAG

Discipline

Artificial Intelligence and Robotics

Areas of Excellence

Digital transformation

Publication

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vienna, Austria, July 27 - August 1

First Page

21863

Last Page

21882

Identifier

10.18653/v1/2025.acl-long.1062

Publisher

Association for Computational Linguistics

City or Country

Vienna

Additional URL

https://doi.org/10.18653/v1/2025.acl-long.1062

Download

Share

COinS