DocMaster: A Hierarchical Structure-Aware System for Document Analysis

2026-07-09

AI Summary

This work addresses the limitation of existing document analysis systems that flatten complex documents into plain text, thereby discarding critical hierarchical structures such as sections, tables, and figures, which hinders effective filtering and in-depth analysis. To overcome this, the authors propose a structure-aware document understanding framework that integrates full document hierarchy into semantic indexing and analysis. The approach constructs a hierarchical document tree by parsing the original layout, leverages large language models to generate structure-aware semantic representations, and introduces a multi-view interactive web interface enabling precise natural language–driven retrieval and question answering. Experiments demonstrate significant improvements in retrieval accuracy and question-answering performance on diverse complex documents, including academic papers, technical manuals, and financial reports. The code and a live demo system are publicly released.

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/.

Problem

• document analysis
• hierarchical structure
• large language models
• semantic indexing
• complex documents

Innovation

• hierarchical document tree
• structure-aware indexing
• large language models
• document analysis
• semantic indexing