Research compares long-document retrieval methods for RAG systems

A new research paper explores different strategies for retrieving information from long documents, comparing methods like full-document scanning, lexical search, dense retrieval, and hybrid approaches. The study found that while full scans can capture more evidence, they don't always lead to better answers and incur higher latency. Hybrid methods, particularly Hybrid + Jev, showed high evidence coverage on books, while Hybrid + Decisions achieved the best answer accuracy. The paper highlights that factors like evidence retention, answer quality, and cost should guide the choice of retrieval strategy for long documents. AI

IMPACT Provides insights into optimizing retrieval strategies for RAG systems, impacting efficiency and accuracy in handling long documents.

RANK_REASON Academic paper presenting novel research findings and comparisons. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Hybrid + Decisions
• Hybrid + Jev
• Influence Flower
• Jev full scan
• Jevíčko
• OpenAI Decisions
• OpenAI dense retrieval
• ScienceCast

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →