Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance the factuality of Large Language Models (LLMs). However, existing RAG systems often suffer from an unfaithfulness issue, where the model's response contradicts evidence from the retrieved context. Existing approaches to improving contextual faithfulness largely rely on external interventions, such as prompt engineering, decoding constraints, or reward-based fine-tuning. These works treat the LLM as a black box and overlook a crucial question: how does the LLM internally integrate retrieved evidence with its parametric memory, particularly under knowledge conflicts? To address this gap, we conduct a probing-based analysis of hidden-state representations in LLMs and observe three findings: knowledge integration occurs hierarchically, conflicts manifest as latent signals at the sentence level, and irrelevant context is often amplified when aligned with parametric knowledge. Building on these findings, we propose CLEAR (Conflict-Localized and Enhanced Attention for RAG), a framework that (i) decomposes context into fine-grained sentence-level knowledge, (ii) employs hidden-state probing to localize conflicting knowledge, and (iii) introduces conflict-aware fine-tuning to guide the model to accurately integrate retrieved evidence. Extensive experiments across three benchmarks demonstrate that CLEAR substantially improves both accuracy and contextual faithfulness, consistently outperforming strong baselines under diverse conflict conditions. The related resources are available at https://github.com/LinfengGao/CLEAR.

翻译：检索增强生成（RAG）已成为增强大语言模型（LLM）事实性的强大范式。然而，现有的RAG系统常常遭受不忠实问题，即模型的响应与检索到的上下文证据相矛盾。现有提升上下文忠实度的方法主要依赖于外部干预，例如提示工程、解码约束或基于奖励的微调。这些工作将LLM视为黑盒，并忽视了一个关键问题：LLM内部如何整合检索到的证据与其参数化记忆，尤其是在知识冲突的情况下？为填补这一空白，我们对LLM的隐藏状态表示进行了基于探针的分析，并观察到三个发现：知识整合是分层进行的，冲突在句子层面表现为潜在信号，并且当无关上下文与参数化知识一致时常常被放大。基于这些发现，我们提出了CLEAR（面向RAG的冲突定位与增强注意力框架），该框架（i）将上下文分解为细粒度的句子级知识，（ii）利用隐藏状态探针定位冲突知识，以及（iii）引入冲突感知微调以指导模型准确整合检索到的证据。在三个基准测试上进行的大量实验表明，CLEAR显著提高了准确性和上下文忠实度，在各种冲突条件下始终优于强基线模型。相关资源可在 https://github.com/LinfengGao/CLEAR 获取。