MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG

• URL: http://arxiv.org/abs/2603.23533v2
• Date: Fri, 27 Mar 2026 05:05:15 GMT
• Title: MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG
• Abstract summary: RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction.<n>We present MDKeyChunker, a three-stage pipeline for Markdown documents that performs structure-aware chunking treating headers, code blocks, tables, and lists as atomic units.<n>The single-call design extracts all seven metadata fields in one LLM invocation, eliminating the need for separate per-field extraction passes.<n>Rolling key propagation replaces hand-tuned scoring with LLM-native semantic matching.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction. We present MDKeyChunker, a three-stage pipeline for Markdown documents that (1) performs structure-aware chunking treating headers, code blocks, tables, and lists as atomic units; (2) enriches each chunk via a single LLM call extracting title, summary, keywords, typed entities, hypothetical questions, and a semantic key, while propagating a rolling key dictionary to maintain document-level context; and (3) restructures chunks by merging those sharing the same semantic key via bin-packing, co-locating related content for retrieval. The single-call design extracts all seven metadata fields in one LLM invocation, eliminating the need for separate per-field extraction passes. Rolling key propagation replaces hand-tuned scoring with LLM-native semantic matching. An empirical evaluation on 30 queries over an 18-document Markdown corpus shows Config D (BM25 over structural chunks) achieves Recall@5=1.000 and MRR=0.911, while dense retrieval over the full pipeline (Config C) reaches Recall@5=0.867. MDKeyChunker is implemented in Python with four dependencies and supports any OpenAI-compatible endpoint.

Related papers

• Improving Long-Context Retrieval with Multi-Prefix Embedding [64.08968715893504]
  Multi-Prefix Embedding partitions a document into chunks separated by EOS tokens, encodes the full sequence in a single causal forward pass, and extracts one embedding at each prefix boundary.<n>MPE retains cross-chunk context, enables chunk-level MaxSim matching, and trains with only document-level relevance labels.
  arXiv  Detail & Related papers  (2026-06-22T17:31:02Z)
• Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets [7.102370558887478]
  We present SLIDERS, a framework for question answering over long document collections through structured reasoning.<n> SLIDERS extracts salient information into a relational database, enabling scalable reasoning over persistent structured state.<n>It outperforms all baselines on three existing long-context benchmarks.
  arXiv  Detail & Related papers  (2026-04-24T07:16:44Z)
• ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization [0.0]
  ONTO is a columnar notation that declares field names once per entity and arranges values in pipe-delimited rows with indentation-based hierarchy.<n>Onto eliminates per-record key repetition while preserving human readability and nested structure support.
  arXiv  Detail & Related papers  (2026-04-19T16:05:33Z)
• M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models [20.44093242908907]
  We propose M3DocDep, an LVLM-based pipeline that first recovers block-level dependencies and then constructs chunks along the recovered document tree.<n>Under a shared-block evaluation protocol, M3DocDep improves STEDS by +28.5 to +39.6 percent on DHP benchmarks, retrieval nDCG by +1.1 to +15.3 percent, and QA ANLS by +4.5 to +15.3 percent on corpus-level RAG benchmarks.
  arXiv  Detail & Related papers  (2026-04-17T05:33:45Z)
• Evidence Units: Ontology-Grounded Document Organization for Parser-Independent Retrieval [0.0]
  Element-level indexing treats every element parsed as an independent chunk, scattering semantically cohesive units across separate retrieval candidates.<n>This paper presents a pipeline that constructs Evidence Units (EUs): semantically complete document chunks that group visual assets with their contextual text.
  arXiv  Detail & Related papers  (2026-04-01T05:32:16Z)
• HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention [62.79085204939384]
  HISA (Hierarchical Indexed Sparse Attention) rewrites the search path from a flat token scan into a two-stage hierarchical procedure.<n>On kernel-level benchmarks, HISA achieves up to speedup at 64K context.
  arXiv  Detail & Related papers  (2026-03-30T13:59:51Z)
• 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)
• 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)
• MAPEX: A Multi-Agent Pipeline for Keyphrase Extraction [17.455890872696894]
  We propose MAPEX, a framework that introduces multi-agent collaboration into keyphrase extraction.<n> MAPEX coordinates LLM-based agents through modules for expert recruitment, candidate extraction, topic guidance, knowledge augmentation, and post-processing.<n>A dual-path strategy dynamically adapts to document length: knowledge-driven extraction for short texts and topic-guided extraction for long texts.
  arXiv  Detail & Related papers  (2025-09-23T09:00:43Z)
• Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval [68.71038700559195]
  Chain of Retrieval(COR) is a novel iterative framework for full-paper retrieval.<n>We present SCIBENCH, a benchmark providing both complete and segmented contexts of full papers for queries and candidates.
  arXiv  Detail & Related papers  (2025-07-14T08:41:53Z)
• IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation [24.108631023133704]
  IterKey is an iterative keyword generation framework that enhances RAG via sparse retrieval.<n>It achieves 5% to 20% accuracy improvements over BM25-based RAG and simple baselines.
  arXiv  Detail & Related papers  (2025-05-13T11:25:15Z)
• PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval [76.50690734636477]
  We propose PromptReps, which combines the advantages of both categories: no need for training and the ability to retrieve from the whole corpus. The retrieval system harnesses both dense text embedding and sparse bag-of-words representations.
  arXiv  Detail & Related papers  (2024-04-29T04:51:30Z)

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.