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

• URL: http://arxiv.org/abs/2601.05265v1
• Date: Sat, 08 Nov 2025 11:45:45 GMT
• Title: Cross-Document Topic-Aligned Chunking for Retrieval-Augmented Generation
• Abstract summary: Cross-Document Topic-Aligned chunking reconstructs knowledge at the corpus level.<n>It first identifies topics across documents, maps segments to each topic, and synthesizes them into unified chunks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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 < 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.

Related papers

• Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG [0.0]
  ToC-guided page retrieval infers headings from visual formatting without LLM calls, embeds them as a parallel index, and loads full page sections.<n>Across 1,280 conditions on 8 enterprise documents, we find ToC is a significant main effect on answer quality.<n>ToC contributes 20% of citations despite adding only 2.9 pages per query.
  arXiv  Detail & Related papers  (2026-06-19T14:33:01Z)
• Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion [0.0]
  We present Query-Adaptive Semantic Chunking (QASC), which dynamically constructs chunks by integrating queries into segmentation through three mechanisms.<n>QASC achieves an F1-score of 0.85, a relative improvement of 18-27% over fixed chunking and 8-12% over semantic and agentic alternatives.
  arXiv  Detail & Related papers  (2026-04-29T06:40:53Z)
• CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents [6.134883925217888]
  We propose CHOP, a framework that iteratively evaluates chunk relevance with Large Language Models (LLMs)<n>CHOP integrates two key components: the CNM-Extractor, which generates compact per-chunk signatures capturing categories, key nouns, and model names, and the Continuity Decision Module, which preserves contextual coherence.<n> Experiments on benchmark datasets show that CHOP alleviates retrieval confusion and provides a scalable approach for building high-quality knowledge bases.
  arXiv  Detail & Related papers  (2026-04-17T08:05:17Z)
• Multi-Vector Index Compression in Any Modality [73.7330345057813]
  Late interaction has emerged as a dominant paradigm for information retrieval in text, images, visual documents, and videos.<n>We introduce four approaches for index compression: sequence resizing, memory tokens, hierarchical pooling, and a novel attention-guided clustering (AGC)<n>AGC uses an attention-guided mechanism to identify the most semantically salient regions of a document as cluster centroids and to weight token aggregation.
  arXiv  Detail & Related papers  (2026-02-24T18:57:33Z)
• Chunk Knowledge Generation Model for Enhanced Information Retrieval: A Multi-task Learning Approach [13.945285357933487]
  This study proposes a method that divides documents into chunk units and generates textual data for each chunk to simultaneously improve retrieval efficiency and accuracy.<n>The proposed "Chunk Knowledge Generation Model" adopts a T5-based multi-task learning structure that simultaneously generates titles and candidate questions from each document chunk.<n> GPT-based evaluation on 305 query-document pairs showed that retrieval using the proposed model achieved 95.41% accuracy at Top@10.
  arXiv  Detail & Related papers  (2025-09-19T06:32:30Z)
• ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links [57.514511353084565]
  We introduce a new domain-agnostic framework for selecting a best-performing approach and annotating cross-document links.<n>We apply our framework in two distinct domains -- peer review and news.<n>The resulting novel datasets lay foundation for numerous cross-document tasks like media framing and peer review.
  arXiv  Detail & Related papers  (2025-09-01T11:32:24Z)
• Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented Generation [4.875345207589195]
  DocsRay is a training-free document understanding system.<n>It integrates pseudo Table of Contents (TOC) generation with hierarchical Retrieval-Augmented Generation (RAG)
  arXiv  Detail & Related papers  (2025-07-31T03:14:45Z)
• Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning [42.35305639777465]
  This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking.<n>We encode textual content using generated questions that span the lexical and semantic space, creating targeted retrieval cues combined with a custom syntactic reranking method.<n>In single-hop retrieval over 109 scientific papers, our approach achieves a Recall@3 of 0.84, outperforming traditional chunking methods by 60 percent.
  arXiv  Detail & Related papers  (2025-06-09T16:15:11Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
  Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge.<n>This paper presents BRIEF, a lightweight approach that performs query-aware multi-hop reasoning.<n>Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
  arXiv  Detail & Related papers  (2024-10-20T04:24:16Z)
• Multi-view Content-aware Indexing for Long Document Retrieval [19.74258792456242]
  Long document question answering (DocQA) aims to answer questions from long documents over 10k words. We propose the Multi-view Content-aware indexing (MC-indexing) for more effective long DocQA. MC-indexing has significantly increased the recall by 42.8%, 30.0%, 23.9%, and 16.3% via top k= 1.5, 3, 5, and 10 respectively.
  arXiv  Detail & Related papers  (2024-04-23T14:55:32Z)
• LOCR: Location-Guided Transformer for Optical Character Recognition [55.195165959662795]
  We propose LOCR, a model that integrates location guiding into the transformer architecture during autoregression. We train the model on a dataset comprising over 77M text-location pairs from 125K academic document pages, including bounding boxes for words, tables and mathematical symbols. It outperforms all existing methods in our test set constructed from arXiv, as measured by edit distance, BLEU, METEOR and F-measure.
  arXiv  Detail & Related papers  (2024-03-04T15:34:12Z)
• How Does Generative Retrieval Scale to Millions of Passages? [68.98628807288972]
  We conduct the first empirical study of generative retrieval techniques across various corpus scales. We scale generative retrieval to millions of passages with a corpus of 8.8M passages and evaluating model sizes up to 11B parameters. While generative retrieval is competitive with state-of-the-art dual encoders on small corpora, scaling to millions of passages remains an important and unsolved challenge.
  arXiv  Detail & Related papers  (2023-05-19T17:33:38Z)
• Differentiable Reasoning over a Virtual Knowledge Base [156.94984221342716]
  We consider the task of answering complex multi-hop questions using a corpus as a virtual knowledge base (KB) In particular, we describe a neural module, DrKIT, that traverses textual data like a KB, softly following paths of relations between mentions of entities in the corpus. DrKIT is very efficient, processing 10-100x more queries per second than existing multi-hop systems.
  arXiv  Detail & Related papers  (2020-02-25T03:13:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.