MoDora: Tree-Based Semi-Structured Document Analysis System
Proceedings of the ACM on Management of Data · 18.05.2026 · 4 (3) · 1-26
DOI: 10.1145/3802089 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 18.05.2026. Verfasst von Bangrui Xu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Key R\\&D Program of China, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China, Shenzhen Project.
Abstract (Originalsprache)
Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts. These documents are widely observed across domains and account for a large portion of real-world data. However, existing methods struggle to support natural language question answering over these documents due to three main technical challenges: (1) The elements extracted by techniques like OCR are often fragmented and stripped of their original semantic context, making them inadequate for analysis. (2) Existing approaches lack effective representations to capture hierarchical structures within documents (e.g., associating tables with nested chapter titles) and to preserve layout-specific distinctions (e.g., differentiating sidebars from main content). (3) Answering questions often requires retrieving and aligning relevant information scattered across multiple regions or pages, such as linking a descriptive paragraph to table cells located elsewhere in the document. To address these issues, we propose Modora, an LLM-powered system for semi-structured document analysis. First, we adopt a local-alignment aggregation strategy to convert OCR-parsed elements into layout-aware components, and conduct type-specific information extraction for components with hierarchical titles or non-text elements. Second, we design the Component-Correlation Tree (CCTree) to hierarchically organize components, explicitly modeling inter-component relations and layout distinctions through a bottom-up cascade summarization process. Finally, we propose a question-type-aware retrieval strategy that supports (1) layout-based grid partitioning for location-based retrieval and (2) LLM-guided pruning for semantic-based retrieval. Experiments show Modora outperforms baselines by 5.97%-61.07% in accuracy. The code is at https://github.com/weAIDB/MoDora.
Förderung
- National Key R\\&D Program of China
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
- Shenzhen Project
- NSF of China
Zitieren
APA
Xu, B., Yao, Q., Tang, Z., Zhou, X., He, Y., Yu, S., Xu, Q., Wang, B., Li, G., He, C., & Wu, F. (2026). MoDora: Tree-Based Semi-Structured Document Analysis System. Proceedings of the ACM on Management of Data, 4(3), 1-26. https://doi.org/10.1145/3802089
Vancouver
Xu B, Yao Q, Tang Z, Zhou X, He Y, Yu S, et al. MoDora: Tree-Based Semi-Structured Document Analysis System. Proceedings of the ACM on Management of Data. 2026;4(3):1-26. doi:10.1145/3802089
BibTeX
@article{Xu2026,
author = {Xu, Bangrui and Yao, Qihang and Tang, Zirui and Zhou, Xuanhe and He, Yeye and Yu, Shihan and Xu, Qianqian and Wang, Bin and Li, Guoliang and He, Conghui and Wu, Fan},
title = {MoDora: Tree-Based Semi-Structured Document Analysis System},
journal = {Proceedings of the ACM on Management of Data},
year = {2026},
volume = {4},
number = {3},
pages = {1--26},
doi = {10.1145/3802089}
}
EUVIMED