From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering

• URL: http://arxiv.org/abs/2604.04948v1
• Date: Mon, 30 Mar 2026 14:40:58 GMT
• Title: From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
• Abstract summary: Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing.<n>No prior study has evaluated PDF processing frameworks by their impact on downstream question-answering accuracy.<n>We compare four open-source PDF-to-Markdown conversion frameworks, Docling, MinerU, Marker, and DeepSeek OCR, across 19 pipeline configurations.
• Score: 32.10503220086596
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing, yet no prior study has evaluated PDF processing frameworks by their impact on downstream question-answering accuracy. We address this gap through a systematic comparison of four open-source PDF-to-Markdown conversion frameworks, Docling, MinerU, Marker, and DeepSeek OCR, across 19 pipeline configurations for extracting text and other contents from PDFs, varying the conversion tool, cleaning transformations, splitting strategy, and metadata enrichment. Evaluation was performed using a manually curated 50-question benchmark over a corpus of 36 Portuguese administrative documents (1,706 pages, ~492K words), with LLM-as-judge scoring averaged over 10 runs. Two baselines bounded the results: naïve PDFLoader (86.9%) and manually curated Markdown (97.1%). Docling with hierarchical splitting and image descriptions achieved the highest automated accuracy (94.1%). Metadata enrichment and hierarchy-aware chunking contributed more to accuracy than the conversion framework choice alone. Font-based hierarchy rebuilding consistently outperformed LLM-based approaches. An exploratory GraphRAG implementation scored only 82%, underperforming basic RAG, suggesting that naïve knowledge graph construction without ontological guidance does not yet justify its added complexity. These findings demonstrate that data preparation quality is the dominant factor in RAG system performance.

Related papers

• VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval [65.89247522243959]
  VisDocAgentBench is a closed-corpus benchmark comparing static and agentic retrieval under a ranked-output contract.<n>It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures.<n>A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context.
  arXiv  Detail & Related papers  (2026-08-18T15:23:06Z)
• LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation [1.0976267899372834]
  LARAG (Link-Aware RAG) is a lightweight, link-aware retrieval strategy that leverages the author-defined hyperlink structure in HTML documentation.<n>LARAG consistently improves answer quality, achieving the highest BERTScore F1, while retrieving fewer chunks and generating fewer tokens.
  arXiv  Detail & Related papers  (2026-05-08T09:50:53Z)
• Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation [0.0]
  Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts.<n>This limits knowledge-retrieval applications that embed large structured knowledge bases directly in the context.<n>We propose Self-Describing Structured Retrieval (SDSR), a lightweight framework in which structured data files embed human-authored navigational metadata at the file's primacy position.
  arXiv  Detail & Related papers  (2026-03-28T14:12:43Z)
• 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)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents [2.657536539253924]
  Existing approaches achieve only 58-64% accuracy on version-sensitive questions.<n>We present VersionRAG, a version-aware RAG framework that explicitly models document evolution.<n>During retrieval, VersionRAG routes queries through specialized paths based on intent classification.
  arXiv  Detail & Related papers  (2025-10-09T11:48:58Z)
• InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering [17.346965728209394]
  Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address key limitations of Large Language Models (LLMs)<n>We propose Document Information Gain (DIG), a novel metric designed to quantify the contribution of retrieved documents to correct answer generation.<n>We introduce InfoGain-RAG, a framework that leverages DIG scores to train a specialized reranker, which prioritizes each retrieved document from exact distinguishing and accurate sorting perspectives.
  arXiv  Detail & Related papers  (2025-09-16T07:28:07Z)
• HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis [55.2480439325792]
  HySemRAG is a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG)<n>System addresses limitations in existing RAG architectures through a multi-layered approach.
  arXiv  Detail & Related papers  (2025-08-01T20:30:42Z)
• LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation [0.432776344138537]
  Large Language Models (LLMs) are capable of natural language understanding and generation.<n> Fine-tuning is one possible solution, but it is resource-intensive and must be repeated with every data update.<n>Retrieval-Augmented Generation (RAG) offers an efficient solution by allowing LLMs to access external knowledge sources.
  arXiv  Detail & Related papers  (2025-06-29T08:22:03Z)
• RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust [50.65321080814249]
  RustRepoTrans is the first repository-level context code translation benchmark targeting incremental translation.<n>We evaluate seven representative LLMs, analyzing their errors to assess limitations in complex translation scenarios.
  arXiv  Detail & Related papers  (2024-11-21T10:00:52Z)
• VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents [66.42579289213941]
  Retrieval-augmented generation (RAG) is an effective technique that enables large language models to utilize external knowledge sources for generation.<n>We introduce VisRAG, which tackles this issue by establishing a vision-language model (VLM)-based RAG pipeline.<n>In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM.
  arXiv  Detail & Related papers  (2024-10-14T15:04:18Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• Evaluating Retrieval Quality in Retrieval-Augmented Generation [21.115495457454365]
  Traditional end-to-end evaluation methods are computationally expensive. We propose eRAG, where each document in the retrieval list is individually utilized by the large language model within the RAG system. eRAG offers significant computational advantages, improving runtime and consuming up to 50 times less GPU memory than end-to-end evaluation.
  arXiv  Detail & Related papers  (2024-04-21T21:22:28Z)
• 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)

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.