重新思考全部证据：通过冲突驱动摘要增强可信的检索增强生成
Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization
AI总结：
本文提出CARE-RAG框架，通过冲突驱动摘要整合检索内容与内部知识，并引入QA Repair修正基准答案，从而在噪声和冲突场景下提升RAG生成的可信度与性能。
摘要：
检索增强生成（RAG）通过将大语言模型（LLM）的参数化知识与外部检索内容相结合来增强其能力。然而，由内部不一致或噪声检索内容引起的知识冲突会严重损害RAG系统的生成可靠性。本文认为，LLM在生成响应之前应重新思考全部证据，包括检索内容和内部知识。我们提出CARE-RAG（面向RAG的冲突感知与可靠证据框架），这是一个通过冲突驱动摘要提升可信度的新型框架。CARE-RAG首先通过比较参数记录来推导参数感知证据，以识别多样的内部视角。然后，它精炼检索到的证据以生成上下文感知证据，去除无关或误导性内容。为了检测和总结冲突，我们蒸馏一个3B LLaMA3.2模型来执行冲突驱动摘要，从而实现跨多个来源的可靠综合。为了进一步确保评估完整性，我们引入QA Repair步骤来纠正过时或模糊的基准答案。在带有检索数据的修订QA数据集上的实验表明，CARE-RAG始终优于强RAG基线，尤其是在具有噪声或冲突证据的场景中。
英文摘要：
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating their parametric knowledge with external retrieved content. However, knowledge conflicts caused by internal inconsistencies or noisy retrieved content can severely undermine the generation reliability of RAG systems.In this work, we argue that LLMs should rethink all evidence, including both retrieved content and internal knowledge, before generating responses.We propose CARE-RAG (Conflict-Aware and Reliable Evidence for RAG), a novel framework that improves trustworthiness through Conflict-Driven Summarization of all available evidence.CARE-RAG first derives parameter-aware evidence by comparing parameter records to identify diverse internal perspectives. It then refines retrieved evidences to produce context-aware evidence, removing irrelevant or misleading content. To detect and summarize conflicts, we distill a 3B LLaMA3.2 model to perform conflict-driven summarization, enabling reliable synthesis across multiple sources.To further ensure evaluation integrity, we introduce a QA Repair step to correct outdated or ambiguous benchmark answers.Experiments on revised QA datasets with retrieval data show that CARE-RAG consistently outperforms strong RAG baselines, especially in scenarios with noisy or conflicting evidence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
