Do Current Retrievers Cover All the Evidence? A Controlled Study of Conjunctive Cross-Page Retrieval
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputation and LanguageInformation Retrieval
AI summaryⓘ
The authors studied how well search systems find long documents that fully satisfy complex requests needing multiple pieces of evidence from different pages. They found that even when a system finds a relevant document, it often misses some required parts, causing a large gap between finding some evidence and all evidence. Their experiments show that breaking down the conditions and using combined text-image methods help, but many improvements still fail to fully cover all needed conditions. The main challenge is ensuring the document actually covers every requested piece, not just finding documents with partial matches.
conjunctive document retrievaldense retrieval modelslexical-visual fusionrerankingGold-NDCGmulti-condition queriesinformation retrievaldocument relevancecondition coveragequery evaluation metrics
Authors
Sungguk Cha, DongWook Kim, Mintae Kim, Youngsub Han, Byoung-Ki Jeon, Sangyeob Lee
Abstract
Finding a long document relevant to a multi-part request is not the same as establishing that it contains every requested piece of evidence. We study this gap for conjunctive document retrieval, where two or three explicit conditions must be supported on different pages of one document. We use n-Clue as a controlled measurement instrument: 1{,}000 queries over 2{,}021 documents pair all-condition golds with naturally occurring documents that satisfy only a subset, and a complete-first success requires a top-10 gold to precede every released subset qrel. Across 70 configurations, condition-wise decomposition improves two dense backbones by 6.8--7.3 points and lexical--visual fusion adds 8.7, while four generic rerankers all reduce Gold-NDCG; these directions replicate on a four-source stress set. Scaling one dense family from 0.6B to 8B changes complete-first success by 0.0 points. The strongest displayed hybrid illustrates the resulting gap: it finds a gold for 81.1\% of queries but succeeds complete-first on only 35.8\%, and the gap persists across condition count, target length, candidate density, query rendering, and the four-source stress set. Finally, page-aware visual systems surface stored support for every condition on only 5.1--5.3\% of queries. These results identify condition coverage, rather than gold discovery alone, as the central bottleneck.