CVSep 24, 2025

Logics-Parsing Technical Report

arXiv:2509.19760v110 citationsh-index: 4Has Code
Originality Incremental advance
AI Analysis

This addresses document parsing for applications requiring layout analysis, but it is incremental as it builds on existing LVLM methods with enhancements.

The paper tackles the limitation of Large Vision-Language models in parsing complex document layouts like multi-column newspapers by proposing Logics-Parsing, an end-to-end model augmented with reinforcement learning, which achieves state-of-the-art performance on a new benchmark of 1,078 PDF images across nine categories.

Recent advances in Large Vision-Language models (LVLM) have spurred significant progress in document parsing task. Compared to traditional pipeline-based methods, end-to-end paradigms have shown their excellence in converting PDF images into structured outputs through integrated Optical Character Recognition (OCR), table recognition, mathematical formula recognition and so on. However, the absence of explicit analytical stages for document layouts and reading orders limits the LVLM's capability in handling complex document types such as multi-column newspapers or posters. To address this limitation, we propose in this report Logics-Parsing: an end-to-end LVLM-based model augmented with reinforcement learning. Our model incorporates meticulously designed reward mechanisms to optimize complex layout analysis and reading order inference. In addition, we expand the model's versatility by incorporating diverse data types such as chemical formulas and handwritten Chinese characters into supervised fine-tuning. Finally, to enable rigorous evaluation of our approach, we introduce LogicsParsingBench, a curated set of 1,078 page-level PDF images spanning nine major categories and over twenty sub-categories, which will be released later. Comprehensive experiments conducted on LogicsParsingBench have validated the efficacy and State-of-the-art (SOTA) performance of our proposed model across diverse document analysis scenarios. Project Page: https://github.com/alibaba/Logics-Parsing

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes