# Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs

arXiv: https://arxiv.org/abs/2607.00596 · HTML: https://mlsanity.com/paper/2607.00596/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [KOSMOS-2.5: A Multimodal Literate Model](https://mlsanity.com/paper/2309.11419/) (2023)
- [DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception](https://mlsanity.com/paper/2410.12628/) (2024)
- [LayoutReader: Pre-training of Text and Layout for Reading Order Detection](https://mlsanity.com/paper/2108.11591/) (2021)
- ['Eclair -- Extracting Content and Layout with Integrated Reading Order for Documents](https://mlsanity.com/paper/2502.04223/) (2025)
- [Multi-Task Handwritten Document Layout Analysis](https://mlsanity.com/paper/1806.08852/) (2018)
- [Page Layout Analysis of Text-heavy Historical Documents: a Comparison of Textual and Visual Approaches](https://mlsanity.com/paper/2212.13924/) (2022)

## Built on by (most cited first, 1 of 1)

- [Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press](https://mlsanity.com/paper/2608.05911/) (2026)

## Abstract (arXiv)

This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We introduce a new annotated dataset of 66 pages and compare geometric heuristics, YOLO-based layout parsing, an end-to-end document model ECLAIR, and a hybrid method combining semantic zone detection with a generative LLM. Our hybrid method achieves the lowest error rates of all evaluated approaches, reducing ordering errors by up to 76% over the strongest geometric baseline, and remains robust in multi-page settings and under noisy OCR. Rather than targeting production the method is designed as a data bootstrapping strategy enabling rapid annotation in highly under-resourced scenarios. Alongside the dataset, we release a specialized Tesseract OCR model for historical Armenian print.