Get Started
Home
Topics
Search
Library
Research questionHow can long-context RAG preserve global document structure during retrieval?Length-based chunking can separate passages from the semantic structure that connects them across a document. Long-context models may also underuse information that appears away from the beginning or end of the context.
AI
Information Retrieval
Natural Language Processing
Retrieval-Augmented Generation
Latest papersRecent research connected to this question, newest first.STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentationThe source studies an LLM-based retriever that uses table-of-contents structure, with ablations in a finetuned Differentiable Search Index system. Evidence comes from SearchTome, a benchmark spanning 18 books across six domains, including Recall@1, hallucination, and few-example generalization results.research paper · Sep 3, 2026
Related questions
How can long-form RAG answer multi-hop questions across changing temporal, spatial, and relational contexts?How can visual-document RAG adapt page retrieval to each query without hurting answer accuracy?How can retrieval-augmented generation reason causally over dynamic external information without losing context?How can structured RAG synthesize evidence scattered across many documents while limiting answer-generation cost?