Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval

• URL: http://arxiv.org/abs/2602.16974v1
• Date: Thu, 19 Feb 2026 00:27:15 GMT
• Title: Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval
• Abstract summary: This paper reproduces prior studies in document chunking and presents a systematic framework that unifies existing strategies.<n>Our evaluation reveals that optimal chunking strategies are task-dependent.
• Score: 37.055995647350784
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Document chunking is a critical preprocessing step in dense retrieval systems, yet the design space of chunking strategies remains poorly understood. Recent research has proposed several concurrent approaches, including LLM-guided methods (e.g., DenseX and LumberChunker) and contextualized strategies(e.g., Late Chunking), which generate embeddings before segmentation to preserve contextual information. However, these methods emerged independently and were evaluated on benchmarks with minimal overlap, making direct comparisons difficult. This paper reproduces prior studies in document chunking and presents a systematic framework that unifies existing strategies along two key dimensions: (1) segmentation methods, including structure-based methods (fixed-size, sentence-based, and paragraph-based) as well as semantically-informed and LLM-guided methods; and (2) embedding paradigms, which determine the timing of chunking relative to embedding (pre-embedding chunking vs. contextualized chunking). Our reproduction evaluates these approaches in two distinct retrieval settings established in previous work: in-document retrieval (needle-in-a-haystack) and in-corpus retrieval (the standard information retrieval task). Our comprehensive evaluation reveals that optimal chunking strategies are task-dependent: simple structure-based methods outperform LLM-guided alternatives for in-corpus retrieval, while LumberChunker performs best for in-document retrieval. Contextualized chunking improves in-corpus effectiveness but degrades in-document retrieval. We also find that chunk size correlates moderately with in-document but weakly with in-corpus effectiveness, suggesting segmentation method differences are not purely driven by chunk size. Our code and evaluation benchmarks are publicly available at (Anonymoused).

Related papers

• When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale [2.7605457369947892]
  We evaluate eight representative chunking strategies across two scalable corpora, three embedding models, and multiple corpus sizes.<n>Our results show that computationally expensive methods rarely provide consistent gains over simpler chunking.
  arXiv  Detail & Related papers  (2026-08-17T13:47:48Z)
• Chunking German Legal Code [0.0]
  We implement and compare a range of segmentation approaches, including structural units (sections, subsections, sentences, propositions), fixed-size windows, contextual chunking, semantic clustering, Lumber-style chunking, and RAPTOR-based hierarchical retrieval.<n>All methods are evaluated on a legal question-answering dataset with section-level gold labels, measuring recall, query latency, index build time, and storage requirements.<n>Results show that chunking strategies aligned with the inherent legal structure - particularly section and subsection - based retrieval-achieve the highest recall, while more complex approaches that override this structure perform worse.
  arXiv  Detail & Related papers  (2026-05-19T13:04:58Z)
• Adaptive Chunking: Optimizing Chunking-Method Selection for RAG [0.0]
  We introduce Adaptive Chunking, a framework that selects the most suitable chunking strategy for each document.<n>On a diverse corpus spanning legal, technical, and social science domains, our metric-merge adaptive method significantly improves downstream RAG performance.
  arXiv  Detail & Related papers  (2026-03-26T11:20:52Z)
• MoDora: Tree-Based Semi-Structured Document Analysis System [62.01015188258797]
  Semi-structured documents integrate diverse interleaved data elements arranged in various and often irregular layouts.<n>MoDora is an LLM-powered system for semi-structured document analysis.<n> Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy.
  arXiv  Detail & Related papers  (2026-02-26T14:48:49Z)
• Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs [0.0]
  Intent-Driven Dynamic Chunking (IDC) is a novel approach that uses predicted user queries to guide document segmentation.<n>We evaluate IDC on six diverse question-answering datasets, including news articles, Wikipedia, academic papers, and technical documentation.
  arXiv  Detail & Related papers  (2026-02-16T14:32:18Z)
• LLM-guided Hierarchical Retrieval [54.73080745446999]
  LATTICE is a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity.<n>A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy.<n>Our framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark.
  arXiv  Detail & Related papers  (2025-10-15T07:05:17Z)
• HiPS: Hierarchical PDF Segmentation of Textbooks [2.2903728931592395]
  Legal textbooks contain layered knowledge essential for interpreting and applying legal norms.<n>We examine a Table of Contents (TOC)-based technique and approaches that rely on open-source structural parsing tools.<n>To enhance parsing accuracy, we incorporate preprocessing strategies such as OCR-based title detection, XML-derived features, and contextual text features.
  arXiv  Detail & Related papers  (2025-08-31T15:40:43Z)
• Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings [25.966475857117175]
  In this work, we introduce ConTEB, a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context.<n>Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required.<n>We propose InSeNT, a novel contrastive post-training approach which combined with late chunking pooling enhances contextual representation learning.
  arXiv  Detail & Related papers  (2025-05-30T16:43:28Z)
• 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)
• Enhanced Retrieval of Long Documents: Leveraging Fine-Grained Block Representations with Large Language Models [24.02950598944251]
  We introduce a novel, fine-grained approach aimed at enhancing the accuracy of relevance scoring for long documents.<n>Our methodology firstly segments a long document into blocks, each of which is embedded using an LLM.<n>We aggregate the query-block relevance scores through a weighted sum method, yielding a comprehensive score for the query with the entire document.
  arXiv  Detail & Related papers  (2025-01-28T16:03:52Z)
• Contextual Document Embeddings [77.22328616983417]
  We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
  arXiv  Detail & Related papers  (2024-10-03T14:33:34Z)
• Document Provenance and Authentication through Authorship Classification [5.2545206693029884]
  We propose an ensemble-based text-processing framework for the classification of single and multi-authored documents. The proposed framework incorporates several state-of-the-art text classification algorithms. The framework is evaluated on a large-scale benchmark dataset.
  arXiv  Detail & Related papers  (2023-03-02T12:26:03Z)
• Value Retrieval with Arbitrary Queries for Form-like Documents [50.5532781148902]
  We propose value retrieval with arbitrary queries for form-like documents. Our method predicts target value for an arbitrary query based on the understanding of layout and semantics of a form. We propose a simple document language modeling (simpleDLM) strategy to improve document understanding on large-scale model pre-training.
  arXiv  Detail & Related papers  (2021-12-15T01:12:02Z)

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.