Research
Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG
arXiv:2610.28957v1 Announce Type: new Abstract: Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval c
arXiv:2610.28957v1 Announce Type: new Abstract: 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.
Related
- Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?
- The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering
- Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA
- When Learned Context Planning Fails to Beat Strong Retrieval: A Controlled Study of Planning, Routing, and Reranking for Long-Context QA
Source: arXiv cs.CL | 2026-10-22