AI RESEARCH
Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG
arXiv CS.CL
•
ArXi:2605.28004v1 Announce Type: new GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question answering. However, existing frameworks extract entities and relations within individual chunks, leaving cross-chunk relations -- those whose evidence spans multiple passages -- systematically absent from the index. Exhaustive LLM-based recovery of such relations is impractical due to the combinatorial explosion of chunk combinations.