ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2502.15543v3
• Date: Sat, 21 Jun 2025 02:55:27 GMT
• Title: ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
• Authors: Pengcheng Huang, Zhenghao Liu, Yukun Yan, Haiyan Zhao, Xiaoyuan Yi, Hao Chen, Zhiyuan Liu, Maosong Sun, Tong Xiao, Ge Yu, Chenyan Xiong,
• Abstract summary: We investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases.<n>We propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs.<n> Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory.
• Score: 91.20492150248106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence. However, they remain susceptible to unfaithful generation, where outputs contradict retrieved context despite its relevance and accuracy. Existing approaches aiming to improve faithfulness primarily focus on enhancing the utilization of external context, but often overlook the persistent influence of internal parametric knowledge during generation. In this work, we investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases. Building on this insight, we propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs and calibrating the model toward retrieved knowledge. To evaluate our approach, we introduce CoFaithfulQA, a benchmark specifically designed to evaluate faithfulness in scenarios where internal knowledge conflicts with accurate external evidence. Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory. These findings underscore the importance of mitigating internal knowledge dominance and provide a new direction for improving LLM trustworthiness in RAG. All codes are available at https://github.com/OpenBMB/ParamMute.

Related papers

• RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence [5.066415370344766]
  Retrieval-Augmented Generation (RAG) is a technique to enhance factual accuracy by integrating external knowledge into the generation process.<n>This paper introduces Radiant, a framework that merges RAG with alignment designed to optimize the interplay between retrieved evidence and generated content.
  arXiv  Detail & Related papers  (2025-06-28T21:40:35Z)
• Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge [19.767087192966223]
  We propose a Dual-Stream Knowledge-Augmented Framework for Shared-Private Semantic Synergy (DSSP-RAG)<n>Central to the framework is a novel approach that refines self-attention into a mixed-attention, distinguishing shared and private semantics for a controlled internal-external knowledge integration.<n>Experiments on benchmark datasets show that DSSP-RAG can effectively resolve conflicts and enhance the complementarity of dual-stream knowledge, leading to superior performance over strong baselines.
  arXiv  Detail & Related papers  (2025-06-06T17:00:23Z)
• Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation [108.13261761812517]
  We introduce FRANQ (Faithfulness-based Retrieval Augmented UNcertainty Quantification), a novel method for hallucination detection in RAG outputs.<n>We present a new long-form Question Answering (QA) dataset annotated for both factuality and faithfulness.
  arXiv  Detail & Related papers  (2025-05-27T11:56:59Z)
• Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG [51.120170062795566]
  We propose Divide-Then-Align (DTA) to endow RAG systems with the ability to respond with "I don't know" when the query is out of the knowledge boundary.<n>DTA balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.
  arXiv  Detail & Related papers  (2025-05-27T08:21:21Z)
• Safety Devolution in AI Agents [56.482973617087254]
  This study investigates how expanding retrieval access affects model reliability, bias propagation, and harmful content generation.<n>Retrieval-augmented agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval.<n>These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-augmented and increasingly autonomous AI systems.
  arXiv  Detail & Related papers  (2025-05-20T11:21:40Z)
• Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Reliable Response Generation in the Wild [11.058848731627233]
  Large language models (LLMs) have advanced information retrieval systems. LLMs often face knowledge conflicts between internal memory and retrievaled external information. We propose Swin-VIB, a novel framework that integrates a pipeline of variational information bottleneck models into adaptive augmentation of retrieved information.
  arXiv  Detail & Related papers  (2025-04-17T14:40:31Z)
• RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects [12.5122702720856]
  We propose Robust Fine-Tuning (RbFT) to enhance the resilience of large language models against retrieval defects.<n> Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions.
  arXiv  Detail & Related papers  (2025-01-30T14:15:09Z)
• Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization [35.269343563526675]
  We propose RHIO, a framework to teach large language models to explicitly discriminate between faithful and unfaithful generations.<n> RHIO first augments unfaithful samples that simulate realistic model-intrinsic errors by selectively masking retrieval heads.<n>These samples are incorporated into joint training, enabling the model to distinguish unfaithful outputs from faithful ones conditioned on control tokens.
  arXiv  Detail & Related papers  (2025-01-23T11:23:25Z)
• What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context [19.78140793942713]
  This paper focuses on LLMs' preferred external knowledge in imperfect contexts when handling multi-hop QA.<n>Inspired by criminal procedural law's Chain of Evidence (CoE), we characterize that knowledge preferred by LLMs should maintain both relevance to the question and mutual support among knowledge pieces.<n>We propose an automated CoE discrimination approach and explore LLMs' preferences from their effectiveness, faithfulness and robustness, as well as CoE's usability in a naive Retrieval-Augmented Generation (RAG) case.
  arXiv  Detail & Related papers  (2024-12-17T07:49:49Z)
• Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models [85.13298925375692]
  Large language models (LLMs) encode vast amounts of knowledge during pre-training. LLMs can be enhanced by incorporating contextual knowledge (CK) Can LLMs effectively integrate their internal PK with external CK to solve complex problems?
  arXiv  Detail & Related papers  (2024-10-10T23:09:08Z)
• Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation [96.78845113346809]
  Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. This paper proposes SynCheck, a lightweight monitor that leverages fine-grained decoding dynamics to detect unfaithful sentences. We also introduce FOD, a faithfulness-oriented decoding algorithm guided by beam search for long-form retrieval-augmented generation.
  arXiv  Detail & Related papers  (2024-06-19T16:42:57Z)
• Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models [51.72963030032491]
  Knowledge documents for large language models (LLMs) may conflict with the memory of LLMs due to outdated or incorrect knowledge. We construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering.
  arXiv  Detail & Related papers  (2024-04-04T16:40:11Z)
• ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents [49.30553350788524]
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to leverage external knowledge. Existing RAG models often treat LLMs as passive recipients of information. We introduce ActiveRAG, a multi-agent framework that mimics human learning behavior.
  arXiv  Detail & Related papers  (2024-02-21T06:04:53Z)
• TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness [58.721012475577716]
  Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge.
  arXiv  Detail & Related papers  (2024-02-19T21:12:14Z)
• "Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs [15.660128743249611]
  Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge. LLMs inevitably require external knowledge during their interactions with users. This raises a crucial question: How will LLMs respond when external knowledge interferes with their parametric knowledge?
  arXiv  Detail & Related papers  (2023-09-15T17:47:59Z)
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation [109.8527403904657]
  We show that large language models (LLMs) possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We propose a simple method to dynamically utilize supporting documents with our judgement strategy.
  arXiv  Detail & Related papers  (2023-07-20T16:46:10Z)
• Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts [21.34852490049787]
  We present the first comprehensive and controlled investigation into the behavior of large language models (LLMs) when encountering knowledge conflicts. We find that LLMs can be highly receptive to external evidence even when that conflicts with their parametric memory. On the other hand, LLMs also demonstrate a strong confirmation bias when the external evidence contains some information consistent with their parametric memory.
  arXiv  Detail & Related papers  (2023-05-22T17:57:41Z)
• Knowledge Rumination for Pre-trained Language Models [77.55888291165462]
  We propose a new paradigm dubbed Knowledge Rumination to help the pre-trained language model utilize related latent knowledge without retrieving it from the external corpus. We apply the proposed knowledge rumination to various language models, including RoBERTa, DeBERTa, and GPT-3.
  arXiv  Detail & Related papers  (2023-05-15T15:47:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.