mlsanityData to 7 Oct 2026

Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation

arXiv 2601.05265 ↗First posted 8 Nov 2025cs.IR cs.AI cs.CLcited by 1

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

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 < 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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 15 of its 18 references that are in the map. First posted on arXiv 8 Nov 2025.

Builds on

15 of 18 references.

References · 15

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  9. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  10. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  11. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  12. 2024Corrective Retrieval Augmented Generationcited by 187
3 more
  1. 2020How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligencecited by 128
  2. 2022Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Datasetcited by 113
  3. 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 70

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
  2. 2024Is Semantic Chunking Worth the Computational Cost?
  3. 2026Adaptive Chunking: Optimizing Chunking-Method Selection for RAG
  4. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
  5. 2026Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion
  6. 2026A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity
  7. 2025A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking
  8. 2026MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval