推理与验证：一种忠实检索增强生成的框架
Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
AI总结：
本文提出了一种领域特定的RAG框架，通过显式推理和验证机制提升检索增强生成的准确性与透明性，在生物医学问答任务中取得显著性能提升。
摘要：
检索增强生成（RAG）显著提高了大型语言模型（LLMs）的事实性，但标准流程往往缺乏验证中间推理的机制，使其在高风险领域容易产生幻觉。为此，我们提出了一种领域特定的RAG框架，集成了显式推理和忠实性验证。我们的架构在标准检索中加入了神经查询重写、基于BGE的交叉编码器重排序以及一个生成理由模块，该模块将子主张根植于特定的证据片段中。我们进一步引入了八类验证分类法，使能够对推理的忠实性进行细粒度评估，区分显式和隐式支持模式，以促进结构化的错误诊断。我们评估了该框架在BioASQ和PubMedQA基准上的表现，特别分析了在受限token预算下动态上下文学习和重排序的影响。实验表明，显式推理生成提高了对vanilla RAG基线的准确性，而动态演示选择结合稳健的重排序在少样本设置中进一步提高了性能。使用Llama-3-8B-Instruct，我们的方法在BioASQ-Y/N上达到了89.1%，在PubMedQA上达到了73.0%，与使用显著更大模型的系统具有竞争力。此外，我们还进行了一项结合人类专家评估与LLM基于验证的试点研究，探讨显式推理生成如何提高系统的透明性，并使在生物医学问答中检索失败的更详细的诊断成为可能。
英文摘要：
Retrieval-Augmented Generation (RAG) significantly improves the factuality of Large Language Models (LLMs), yet standard pipelines often lack mechanisms to verify inter- mediate reasoning, leaving them vulnerable to hallucinations in high-stakes domains. To address this, we propose a domain-specific RAG framework that integrates explicit rea- soning and faithfulness verification. Our architecture augments standard retrieval with neural query rewriting, BGE-based cross-encoder reranking, and a rationale generation module that grounds sub-claims in specific evidence spans. We further introduce an eight-category verification taxonomy that enables fine-grained assessment of rationale faithfulness, distinguishing between explicit and implicit support patterns to facilitate structured error diagnosis. We evaluate this framework on the BioASQ and PubMedQA benchmarks, specifically analyzing the impact of dynamic in-context learning and rerank- ing under constrained token budgets. Experiments demonstrate that explicit rationale generation improves accuracy over vanilla RAG baselines, while dynamic demonstration selection combined with robust reranking yields further gains in few-shot settings. Using Llama-3-8B-Instruct, our approach achieves 89.1% on BioASQ-Y/N and 73.0% on Pub- MedQA, competitive with systems using significantly larger models. Additionally, we perform a pilot study combining human expert assessment with LLM-based verification to explore how explicit rationale generation improves system transparency and enables more detailed diagnosis of retrieval failures in biomedical question answering.
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。
