LongRefiner refines long RAG contexts by building an XML tree of the document, scoring nodes with local and global relevance, and selecting a compact subset that improves QA accuracy on seven datasets while cutting token usage versus full-document input.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Document Refinement for Long-context Retrieval-augmented Generation
LongRefiner refines long RAG contexts by building an XML tree of the document, scoring nodes with local and global relevance, and selecting a compact subset that improves QA accuracy on seven datasets while cutting token usage versus full-document input.