具有迭代推理的有状态证据驱动检索增强生成
Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
AI总结：
本文提出一种具有迭代推理的有状态证据驱动检索增强生成框架，通过逐步积累证据提升问答稳定性与鲁棒性，在多个基准测试中表现出色。
AI中文摘要：
检索增强生成（RAG）使大型语言模型（LLMs）能够依赖外部知识，但常常面临扁平的上下文表示和无状态检索，导致性能不稳定。我们提出具有迭代推理的有状态证据驱动RAG，将问答过程建模为逐步证据积累过程。检索到的文档被转换为具有显式相关性和置信度信号的结构化推理单元，并在持久化证据池中保持，该池捕捉支持和不支持信息。该框架执行证据驱动的缺陷分析以识别差距和冲突，并迭代优化查询以引导后续检索。这种迭代推理过程实现了稳定的证据聚合并提高了对噪声检索的鲁棒性。在多个问答基准测试中的实验表明，该方法在标准RAG和多步骤基线方面表现一致提升，同时有效积累高质量证据并在大量检索噪声下保持稳定性能。
英文摘要：
Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful Evidence-Driven RAG with Iterative Reasoning, a framework that models question answering as a progressive evidence accumulation process. Retrieved documents are converted into structured reasoning units with explicit relevance and confidence signals and maintained in a persistent evidence pool capturing both supportive and non-supportive information. The framework performs evidence-driven deficiency analysis to identify gaps and conflicts and iteratively refines queries to guide subsequent retrieval. This iterative reasoning process enables stable evidence aggregation and improves robustness to noisy retrieval. Experiments on multiple question answering benchmarks demonstrate consistent improvements over standard RAG and multi-step baselines, while effectively accumulating high-quality evidence and maintaining stable performance under substantial retrieval noise.
