# Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi

arXiv: https://arxiv.org/abs/2606.28796 · HTML: https://mlsanity.com/paper/2606.28796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [Augmenting Neural Networks with First-order Logic](https://mlsanity.com/paper/1906.06298/) (2019)
- [L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources](https://mlsanity.com/paper/2202.01159/) (2022)
- [On Limitations of LLM as Annotator for Low Resource Languages](https://mlsanity.com/paper/2411.17637/) (2024)

## Abstract (arXiv)

Government documents in India are predominantly issued in regional languages such as Marathi, creating substantial accessibility barriers for non-native readers, interstate administrative bodies, and policy analysts. Although recent advances in neural machine translation have improved sentence-level translation quality, existing systems largely neglect document structure, formatting integrity, and domain-specific terminology, thereby limiting their applicability to official documentation. This paper presents a structure-preserving Marathi-to-English government document translation framework capable of performing end-to-end document transformation while maintaining layout fidelity. The proposed system integrates layout-aware optical character recognition, coordinate-based text extraction, large language model based translation, and structured document reconstruction through HTML representations. By enforcing spatial alignment constraints and preserving hierarchical document elements, the framework ensures structural consistency between the source and translated documents. Experimental evaluation on real-world Marathi government PDFs demonstrates improved structural preservation, translation coherence, and terminological consistency compared to conventional text-only translation pipelines. The proposed framework contributes toward scalable multilingual accessibility solutions for e-governance and administrative document processing.