This work presents DocMaster, a hierarchical structure-aware document analysis system that parses documents into hierarchical document trees preserving original layouts and constructs a structure-aware semantic index that enables accurate document filtering and in-depth analysis.
Abstract
Leveraging large language models (LLMs) to analyze complex documents -- such as academic papers, technical manuals, and financial reports -- has emerged as a mainstream and critical task in both research and industry. In practice, users must first filter relevant documents from large collections and then conduct in-depth analysis (e.g. question answering) over the selected subset, yet existing systems flatten documents into plain-text chunks, discarding the rich hierarchical structures (sections, tables, figures, equations) and degrading downstream performance. We present DocMaster, a hierarchical structure-aware document analysis system. DocMaster parses documents into hierarchical document trees preserving original layouts and constructs a structure-aware semantic index that enables accurate document filtering and in-depth analysis. We demonstrate DocMaster through an interactive web interface that enables users to upload document collections, construct tree-based and multi-view semantic indices, filter relevant documents via natural-language conditions, and perform follow-up question answering over the filtered results. The source code, data, and demo are available at https://doc-master.github.io/.
In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relations remains challenging in multi-page documents with long-range dependencies and heterogeneous layouts. To address this, we propose a tree-guided and self-regressive framework, termed DOcument Structure Analyzer (DOSA), for inferring relations among page objects and reconstructing document-level semantic trees. DOSA processes documents chunk-by-chunk, fusing visual, textual, and layout features for each page object and predicting hierarchical and ordering relations. The predicted relations are used to incrementally construct a semantic tree, which is then leveraged as structural context to guide inference on subsequent chunks. Experimental results on five benchmarks demonstrate the effectiveness of DOSA, with improvements of up to 4 F1 points and 19 TEDS points on DocHieNet, the most challenging multi-page hierarchy benchmark.
Bohou Li, Ben Sowell, Mehul A. Shah et al.· 0 citations
Long-document question-answering experiments show that human-verified TOC hierarchies and contextual relationships improve reasoning, with their combination providing complementary benefits.
Yuefeng Zou, Yichen Lu, Jingxiao Yang et al.· 0 citations
Documents remain one of the primary carriers of knowledge in scientific, enterprise, and governmental settings, yet their complex visual structure—comprising layouts, tables, figures, and multi-column text—poses significant challenges for modern AI systems. Large language models do not natively understand such document structures, while traditional PDF parsers often lose semantic and structural information, leading to noisy or incomplete representations. In this talk, we present Docling, an open-source document processing framework designed to transform heterogeneous documents into high-quality, structured representations suitable for AI applications. Docling combines layout analysis, OCR, table structure recognition, and document assembly into a unified pipeline that produces rich, LLM-friendly outputs such as structured JSON and Markdown while preserving visual grounding and reading order. The framework supports multiple input formats and integrates with modern AI ecosystems, enabling applications including retrieval-augmented generation, schema-based information extraction, and agent-driven workflows. We discuss the architecture of Docling, its emerging ecosystem of models and tools, and its role in enabling scalable, privacy-preserving document intelligence through local execution and open standards. By bridging the gap between visually complex documents and machine-readable knowledge, Docling provides a foundation for reliable document understanding in next-generation AI systems.
P. Staar· Proceedings of the 2026 ACM...· 0 citations
The design realization and evaluation of an Automated Summarization Tool (AST) is presented which is a document intelligence platform based on google gemini 2.5 flash that outperforms the strongest fine-tuned transformer baselines (PEGASUS, BART) by ~14 points and is clearly ahead of BERTSUM-ext (a strong transformer baseline), Pointer-Generator Network, TextRank.
K. Kumar, A. Amandeep, Dharmender Kumar et al.· International Journal of Inn...· 0 citations
The exponential growth of textual data, in the form of corporate documents, reports, and research papers, in the current digital era has increased the need for intelligent systems that can automatically comprehend documents. Analysing these documents by hand is ineffective and time-consuming. In order to extract valuable insights from documents, this study provides an AI- Based document analyzer with a question-answer system that makes use of Natural Language Processing approaches. Users can submit text or PDF files to the system, which then extracts content, generates succinct summaries, identifies keywords, and enables interactive question-answering. Python is used to build the architecture, which is then serverless deployed on Amazon Web Services (AWS) utilising Amazon S3 and Amazon EC2, and for the question-answering system, GEMINI is used. By reducing reading time and providing immediate access to pertinent information, the suggested solution increases productivity. It is affordable, scalable, and suitable for business, education, and research.
Radhika Sharma, Devraj Gautam· Revolutionary Advances in Co...· 0 citations
Due to the surge in digital document creation, intelligent systems that can effectively retrieve accurate information from unstructured PDF content have become a necessity. Current keyword-based search techniques lack semantic meaning, while large language models (LLMs), when utilized individually, produce hallucinated results when they are not contextually aware of document content. In this paper, we introduce a novel real-time question answering system for PDF content using a lightweight approach to Retrieval-Augmented Generation (RAG). Our system combines a HuggingFace sentence transformer model for semantic embeddings with a FAISS vector similarity search for efficient retrieval, leveraging a Groq-hosted LLaMA 3.3 70B model for context-grounded answer generation. The system is built using LangChain for orchestration and Streamlit for web-based deployment, and requires no GPU, no fine-tuning, and no pre-indexed corpus. Evaluation across five complementary metrics—Exact Match, Token-level F1, BLEU, ROUGE, and semantic similarity—demonstrates strong alignment between generated and reference answers, with a peak semantic similarity of 0.8709 and a mean Token F1 of 0.4701, confirming the viability of this approach for real-world document intelligence.
Mukesh Lakshmi Sai Medikonda, Kalva Vishnu Teja, K. Greeshma et al.· International Conference Com...· 0 citations