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 (Code and Data).

翻译：可靠的检索增强生成（RAG）系统根本上依赖于检索器查找相关信息的能力。我们发现，RAG系统中使用的神经检索器存在盲点，我们将其定义为未能检索到与查询相关但与查询嵌入相似度较低的实体。我们研究了导致此类盲点实体被映射到嵌入空间不可访问区域的训练诱导偏差，从而造成其可检索性低下。利用基于维基数据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），我们证明标准检索器（如CONTRIEVER、REASONIR）中的盲点风险可以通过实体嵌入几何结构在索引前进行预测，从而避免昂贵的检索评估。为解决这些盲点，我们提出了ARGUS流程，该流程通过从知识库（在本研究中为维基百科首段）进行针对性文档增强，使高风险（低RPS）实体变得可检索。在BRIGHT、IMPLIRET和RAR-B数据集上的大量实验表明，ARGUS在所有评估的检索器上均取得了一致的改进（平均提升+3.4 nDCG@5和+4.5 nDCG@10绝对分），且在具有挑战性的子集中提升幅度显著更大。这些结果证实，预先补救盲点对于构建稳健可信的RAG系统至关重要（代码与数据已公开）。