FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
This addresses the issue of unfaithful outputs in RAG systems for users relying on accurate knowledge-intensive tasks, representing a novel method rather than an incremental improvement.
The paper tackles the problem of unfaithfulness in retrieval-augmented generation (RAG) systems, where models generate outputs that ignore or inconsistently blend retrieved context with parametric knowledge, especially during knowledge conflicts. The result is FaithfulRAG, a framework that explicitly models fact-level conflicts and uses a self-thinking process to integrate conflicting facts, outperforming state-of-the-art methods in experiments.
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