# Seg2Act: Global Context-aware Action Generation for Document Logical Structuring

arXiv: https://arxiv.org/abs/2410.06802 · HTML: https://mlsanity.com/paper/2410.06802/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Dense Hierarchical Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2110.15439/) (2021)
- [PDFTriage: Question Answering over Long, Structured Documents](https://mlsanity.com/paper/2309.08872/) (2023)
- [Multimodal Tree Decoder for Table of Contents Extraction in Document Images](https://mlsanity.com/paper/2212.02896/) (2022)
- [Abstractive Summarization Guided by Latent Hierarchical Document Structure](https://mlsanity.com/paper/2211.09458/) (2022)
- [Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser](https://mlsanity.com/paper/2105.00150/) (2021)
- [Table-Of-Contents generation on contemporary documents](https://mlsanity.com/paper/1911.08836/) (2019)
- [A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports](https://mlsanity.com/paper/2310.18073/) (2023)

## Built on by (most cited first, 2 of 2)

- [Document Intelligence in the Era of Large Language Models: A Survey](https://mlsanity.com/paper/2510.13366/) (2025)
- [BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints](https://mlsanity.com/paper/2609.07362/) (2026)

## Abstract (arXiv)

Document logical structuring aims to extract the underlying hierarchical structure of documents, which is crucial for document intelligence. Traditional approaches often fall short in handling the complexity and the variability of lengthy documents. To address these issues, we introduce Seg2Act, an end-to-end, generation-based method for document logical structuring, revisiting logical structure extraction as an action generation task. Specifically, given the text segments of a document, Seg2Act iteratively generates the action sequence via a global context-aware generative model, and simultaneously updates its global context and current logical structure based on the generated actions. Experiments on ChCatExt and HierDoc datasets demonstrate the superior performance of Seg2Act in both supervised and transfer learning settings.