{"ID":2844627,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.05265","arxiv_id":"2601.05265","title":"Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation","abstract":"Chunking quality determines RAG system performance. Current methods partition documents individually, but complex queries need information scattered across multiple sources: the knowledge fragmentation problem. We introduce Cross-Document Topic-Aligned (CDTA) chunking, which reconstructs knowledge at the corpus level. It first identifies topics across documents, maps segments to each topic, and synthesizes them into unified chunks. On HotpotQA multi-hop reasoning, our method reached 0.93 faithfulness versus 0.83 for contextual retrieval and 0.78 for semantic chunking, a 12% improvement over current industry best practice (p \u003c 0.05). On UAE Legal texts, it reached 0.94 faithfulness with 0.93 citation accuracy. At k = 3, it maintains 0.91 faithfulness while semantic methods drop to 0.68, with a single CDTA chunk containing information requiring multiple traditional fragments. Indexing costs are higher, but synthesis produces information-dense chunks that reduce query-time retrieval needs. For high-query-volume applications with distributed knowledge, cross-document synthesis improves measurably over within-document optimization.","short_abstract":"Chunking quality determines RAG system performance. Current methods partition documents individually, but complex queries need information scattered across multiple sources: the knowledge fragmentation problem. We introduce Cross-Document Topic-Aligned (CDTA) chunking, which reconstructs knowledge at the corpus level....","url_abs":"https://arxiv.org/abs/2601.05265","url_pdf":"https://arxiv.org/pdf/2601.05265v1","authors":"[\"Mile Stankovic\"]","published":"2025-11-08T11:45:45Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.CL\"]","methods":"[\"RAG\"]","has_code":false}