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

arXiv: https://arxiv.org/abs/2601.05265 · HTML: https://mlsanity.com/paper/2601.05265/

## Key facts

- Cited by 1 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence](https://mlsanity.com/paper/2004.12158/) (2020)
- [Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset](https://mlsanity.com/paper/2207.00220/) (2022)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)

## Built on by (most cited first, 1 of 1)

- [MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG](https://mlsanity.com/paper/2603.23533/) (2026)

## 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.