长文档 RAG 该全量扫描还是检索索引？11 种配置对比给出答案
Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG
用 396 个 QASPER 问题和 8 本教材实测了 11 种长文档检索方案，结论挺反直觉：扫全文不一定更强，Hybrid + Jev 证据覆盖 94.1% 还更快更省钱。
论文比较了 11 种检索配置，覆盖词法检索、稠密检索、混合重排和全文档扫描。评测使用 396 个 QASPER 问题和来自 8 本完整教材的 80 个问题。在教材场景中，Hybrid + Jev 的证据覆盖率最高，达 94.1%，高于 Jev 全量扫描的 88.7% 和 OpenAI 稠密检索的 81.3%。但证据覆盖率与答案质量并不完全一致：Hybrid + Decisions 的教材答案准确率达到 0.892，为各检索方法中最高，尽管其找回的参考证据更少。全量扫描延迟明显更高，而可复用的稠密检索在查询量增加时预估 API 成本低于付费决策类方法。
Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG
Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval configurations spanning lexical and dense search, hybrid reranking, and full-document scanning with Jev, OpenAI Decisions, and Cloudflare Clef. Our evaluation uses 396 QASPER questions and 80 questions from eight complete textbooks, with common passages, a five-passage limit, and a fixed answer generator. On books, Hybrid + Jev achieves the highest observed evidence coverage (94.1%), compared with 88.7% for Jev full scan and 81.3\% for OpenAI dense retrieval. Full scans examine every passage initially, yet later reduction steps can discard relevant evidence. Higher evidence coverage also does not consistently produce better answers: Hybrid + Decisions achieves the highest observed book Answer Accuracy among retrieval methods (0.892), despite recovering less reference evidence. Full scanning incurs substantially higher latency on books under the tested deployments, while reusable dense retrieval has lower projected API cost than paid decision-based methods as queries accumulate. Most QASPER articles already fit within the hybrid candidate pool, limiting the benefit of scanning. These results highlight evidence retention, answer quality, and reuse cost as complementary criteria for choosing a long-document retrieval strategy.
