用Argus之眼：通过不确定性评分评估检索缺口以检测并弥补检索盲区
With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots
AI总结：
ARGUS通过文档增强技术提升检索器对高风险实体的检索能力，有效减少检索盲区，提高RAG系统的可靠性。
摘要：
可靠的检索增强生成（RAG）系统依赖于检索器找到相关信息的基本能力。我们证明，用于RAG系统的神经检索器存在盲区，我们将其定义为无法检索与查询相关但与查询嵌入相似度低的实体。我们研究了导致此类盲区实体被映射到嵌入空间不可达部分的训练诱导偏差，从而导致检索性低。使用从Wikidata关系和维基百科首段构建的大规模数据集，以及我们提出的检索概率评分（RPS），我们表明标准检索器（如CONTRIEVER、REASONIR）中的盲区风险可通过实体嵌入几何在索引前预测，避免昂贵的检索评估。为解决这些盲区，我们引入ARGUS，一个管道，通过从知识库（KB）、维基百科首段等来源进行针对性文档增强，使高风险（低RPS）实体的可检索性得以提升。在BRIGHT、IMPLIRET和RAR-B上的大量实验表明，ARGUS在所有评估的检索器上均实现了持续改进（平均nDCG@5提升+3.4，nDCG@10提升+4.5个绝对点），在具有挑战性的子集上提升幅度更大。这些结果表明，预先弥补盲区对于构建稳健和可信的RAG系统至关重要（代码和数据）
英文摘要：
Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information. We show that neural retrievers used in RAG systems have blind spots, which we define as the failure to retrieve entities that are relevant to the query, but have low similarity to the query embedding. We investigate the training-induced biases that cause such blind spot entities to be mapped to inaccessible parts of the embedding space, resulting in low retrievability. Using a large-scale dataset constructed from Wikidata relations and first paragraphs of Wikipedia, and our proposed Retrieval Probability Score (RPS), we show that blind spot risk in standard retrievers (e.g., CONTRIEVER, REASONIR) can be predicted pre-index from entity embedding geometry, avoiding expensive retrieval evaluations. To address these blind spots, we introduce ARGUS, a pipeline that enables the retrievability of high-risk (low-RPS) entities through targeted document augmentation from a knowledge base (KB), first paragraphs of Wikipedia, in our case. Extensive experiments on BRIGHT, IMPLIRET, and RAR-B show that ARGUS achieves consistent improvements across all evaluated retrievers (averaging +3.4 nDCG@5 and +4.5 nDCG@10 absolute points), with substantially larger gains in challenging subsets. These results establish that preemptively remedying blind spots is critical for building robust and trustworthy RAG systems.
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。
