FAIR-RAG：面向检索增强生成的可信自适应迭代精炼
FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation
AI总结：
FAIR-RAG通过结构化证据评估和自适应查询精炼的迭代循环，显式识别并填补证据缺口，显著提升多跳问答的准确性与可信度。
摘要：
尽管检索增强生成（RAG）缓解了大语言模型（LLMs）中的幻觉和知识陈旧问题，但现有框架在处理需要综合不同来源信息的复杂多跳查询时常常表现不佳。当前先进的RAG方法采用迭代或自适应策略，但缺乏一种稳健的机制来系统地识别和填补证据缺口，常常传播噪声或未能收集全面的上下文。我们提出了FAIR-RAG，一种新颖的智能体框架，将标准RAG流程转变为动态的、证据驱动的推理过程。其核心是一个由我们称为结构化证据评估（SEA）模块控制的迭代精炼循环。SEA充当一种分析性门控机制：它将初始查询分解为所需发现的检查清单，并审计聚合的证据以识别已确认的事实，以及关键的、明确的信息缺口。这些缺口为自适应查询精炼智能体提供了精确的信号，该智能体生成新的、有针对性的子查询以检索缺失信息。此循环持续进行，直到证据被验证为充分，确保为最终严格可信的生成提供全面的上下文。我们在具有挑战性的多跳问答基准上进行了实验，包括HotpotQA、2WikiMultiHopQA和MusiQue。在统一的实验设置下，FAIR-RAG显著优于强基线。在HotpotQA上，它达到了0.453的F1分数——比最强的迭代基线绝对提高了8.3个百分点——在这些基准上为此类方法建立了新的最先进水平。我们的工作表明，带有显式缺口分析的结构化、证据驱动的精炼过程对于在先进RAG系统中实现复杂、知识密集型任务的可靠和准确推理至关重要。
英文摘要：
While Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in Large Language Models (LLMs), existing frameworks often falter on complex, multi-hop queries that require synthesizing information from disparate sources. Current advanced RAG methods, employing iterative or adaptive strategies, lack a robust mechanism to systematically identify and fill evidence gaps, often propagating noise or failing to gather a comprehensive context. We introduce FAIR-RAG, a novel agentic framework that transforms the standard RAG pipeline into a dynamic, evidence-driven reasoning process. At its core is an Iterative Refinement Cycle governed by a module we term Structured Evidence Assessment (SEA). The SEA acts as an analytical gating mechanism: it deconstructs the initial query into a checklist of required findings and audits the aggregated evidence to identify confirmed facts and, critically, explicit informational gaps. These gaps provide a precise signal to an Adaptive Query Refinement agent, which generates new, targeted sub-queries to retrieve missing information. This cycle repeats until the evidence is verified as sufficient, ensuring a comprehensive context for a final, strictly faithful generation. We conducted experiments on challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, and MusiQue. In a unified experimental setup, FAIR-RAG significantly outperforms strong baselines. On HotpotQA, it achieves an F1-score of 0.453 -- an absolute improvement of 8.3 points over the strongest iterative baseline -- establishing a new state-of-the-art for this class of methods on these benchmarks. Our work demonstrates that a structured, evidence-driven refinement process with explicit gap analysis is crucial for unlocking reliable and accurate reasoning in advanced RAG systems for complex, knowledge-intensive tasks.
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。
