--- title: "EvaHan 2026 Ancient Books Multimodal OCR and Layout" description: "This system report describes one team's entry to EvaHan 2026, a shared task on OCR for ancient Chinese books with… 11 references." authors: ["Chenrui Zheng"] year: 2026 venue: "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026" source: "https://aclanthology.org/2026.lt4hala-1.28/" doi: "10.63317/3n7j6t59tuhs" licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)" licence_url: "https://creativecommons.org/licenses/by-nc/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/zheng-2026-evahan-2026-ancient-books-multimodal/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zheng-2026-evahan-2026-ancient-books-multimodal/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/) / EvaHan 2026 Ancient Books Multimodal OCR and Layout Analysis System Technical Report # EvaHan 2026 Ancient Books Multimodal OCR and Layout Analysis System Technical Report **Authors:** Chenrui Zheng · **Year:** 2026 · **Venue:** [Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/lt4hala/) ([Workshop on Language Technologies for Historical and Ancient Languages @ LREC 2026](https://md.research.elamur.ai/free/en/venues/lt4hala/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.lt4hala-1.28/) · [PDF](https://aclanthology.org/2026.lt4hala-1.28.pdf) · [DOI 10.63317/3n7j6t59tuhs](https://doi.org/10.63317/3n7j6t59tuhs) · [OpenAlex](https://openalex.org/W7166572473) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary This system report describes one team's entry to EvaHan 2026, a shared task on OCR for ancient Chinese books with multimodal LLMs. The task has three parts: printed text recognition (Task A, CER), layout element detection of text, image, book_edge and seal (Task B, mAP@[.5:.95]), and handwritten text recognition (Task C, CER). Under the Closed Modality rule, the author fine-tuned Qwen2.5-VL-7B-Instruct. The approach combines three things: - **Cleaner data:** punctuation was removed, repetition marks were swapped for a placeholder token and restored afterwards, and Task B annotations were corrected by hand. - **Synthetic data:** hard-character samples and recombined layouts were generated. - **Staged training:** a curriculum ordered by difficulty, mainly with LoRA, and with full-parameter and GRPO variants tested for Task B. On a local validation split, staged training clearly beat plain SFT for both character recognition and layout detection. GRPO destabilised training, and the hardest layouts caused repetition loops. For historical-text digitisation, the main lesson is that data cleaning and curriculum design matter at least as much as the training algorithm. Code and synthetic data are released on GitHub. ## Key points - **Data split:** each official dataset has about 5,000 image–text pairs, split 9:1 into 4,500 training and 500 validation samples. For Task B, 480 images with unreliable or overly complex annotations were dropped. - **Synthetic data:** - 1,000 hard-character samples for Tasks A and C, built from characters that Qwen2.5-VL-72B misread. - 2,500 recombined layout images for Task B. - **Task B curriculum:** K-Means clustering on element count, density and overlap produced three difficulty levels: Easy (2,400), Medium (949) and Hard (723). - **Validation CER:** - Task A fell from 10.0% to 2.0% (Stage 1) and was 3.0% after Stage 2. - Task C fell from 22.0% to 10.0% after Stage 2. - **Task B results:** - The paper reports a gain of 10.9 percentage points in mAP over its baseline. - The submitted model, Stage1-LoRA + Stage2-Full + Stage3-Full, reached roughly 0.51 mAP, compared with 0.47 for direct SFT. These figure values come from a garbled plot. - GRPO did not help and made training unstable. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) — University, Guangzhou, China · 72 works · 9,502 citations 📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 188 works · [⚙️ Media Technology](https://md.research.elamur.ai/free/en/shelves/engineering/media-technology/) · 42 works 🧭 Topics (1): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works ## Cite Cite as: Chenrui Zheng. 2026. EvaHan 2026 Ancient Books Multimodal OCR and Layout Analysis System Technical Report. Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{zheng2026evahan, title = {{EvaHan 2026 Ancient Books Multimodal OCR and Layout Analysis System Technical Report}}, author = {Chenrui Zheng}, booktitle = {Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026}, year = {2026}, doi = {10.63317/3n7j6t59tuhs}, url = {https://doi.org/10.63317/3n7j6t59tuhs} } ``` - [← previous EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks](https://md.research.elamur.ai/free/en/papers/lu-2026-eva-evolving-semantic-adversaries-red/) - [next → Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/yu-2026-eval-rar-evaluation-driven-retrieval/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/32/) ## References 11 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. B. Wang, C. Xu, X. Zhao, et al., “[MinerU: An Open-Source Solution for Precise Document Content Extraction](https://md.research.elamur.ai/free/en/papers/wang-2024-mineru-open-source-solution-precise/),” arXiv:2409.18839, 2024. 2. Baidu. PP-Structure: Document Structure Analysis. [https://github.com/PaddlePaddle/](https://github.com/PaddlePaddle/) PaddleOCR, 2024. [↗](https://github.com/PaddlePaddle/) 3. Y. Bengio, J. Louradour, R. Collobert, and J. Weston, “[Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/),” in Proceedings of the 26th Annual International Conference on Machine Learning (ICML), pp. 41-48, 2009. 4. F. Borisyuk, A. Gordo, and V. Sivakumar, “Rosetta: Large scale system for text detection and recognition in images,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 71-79, 2018. [find](https://scholar.google.com/scholar?q=F%2E+Borisyuk%2C+A%2E+Gordo%2C+and+V%2E+Sivakumar%2C+%E2%80%9CRosetta%3A+Large+scale+system+for+text+detection+and+recognition+in+images%2C%E2%80%9D+in+Proceedings+of+the+24th+ACM+SIGKDD+International+Conference+on+Knowledge+Discove) 5. C. Cui, T. Sun, M. Lin, et al., “PaddleOCR 3.0 Technical Report,” arXiv preprint arXiv:2507.05595v1, 2025. — [arXiv:2507.05595](https://arxiv.org/abs/2507.05595) [find](https://scholar.google.com/scholar?q=C%2E+Cui%2C+T%2E+Sun%2C+M%2E+Lin%2C+et+al%2E%2C+%E2%80%9CPaddleOCR+3%2E0+Technical+Report%2C%E2%80%9D+arXiv+preprint+arXiv%3A2507%2E05595v1%2C+2025%2E+%E2%80%94+%5BarXiv%3A2507%2E05595%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2507%2E05595%29) 6. H. Li, Y. Liu, W. Liao, et al., “Optical Character Recognition in the Era of Large Models: Status and Prospect,” Journal of Image and Graphics, vol. 30, no. 6, pp. 2023-2050, 2025. [find](https://scholar.google.com/scholar?q=H%2E+Li%2C+Y%2E+Liu%2C+W%2E+Liao%2C+et+al%2E%2C+%E2%80%9COptical+Character+Recognition+in+the+Era+of+Large+Models%3A+Status+and+Prospect%2C%E2%80%9D+Journal+of+Image+and+Graphics%2C+vol%2E+30%2C+no%2E+6%2C+pp%2E+2023%2D2050%2C+2025%2E) 7. J. Niu, Z. Liu, Z. Gu, et al., “[MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://md.research.elamur.ai/free/en/papers/niu-2026-mineru2-5-decoupled-vision-language/),” arXiv:2509.22186, 2025. 8. J. Poznanski, A. Rangapur, J. Borchardt, et al., “[olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://md.research.elamur.ai/free/en/papers/poznanski-2025-olmocr-unlocking-trillions-tokens-pdfs/),” arXiv:2502.18443, 2025. 9. R. Saini et al., “ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family Records,” in IEEE International Conference on Document Analysis and Recognition (ICDAR), 2019. [find](https://scholar.google.com/scholar?q=R%2E+Saini+et+al%2E%2C+%E2%80%9CICDAR+2019+Historical+Document+Reading+Challenge+on+Large+Structured+Chinese+Family+Records%2C%E2%80%9D+in+IEEE+International+Conference+on+Document+Analysis+and+Recognition+%28ICDAR%29%2C+2019%2E) 10. P. Soviany, R. T. Ionescu, P. Rota, and N. Sebe, “Curriculum Learning: A Survey,” International Journal of Computer Vision, vol. 130, pp. 877– 902, 2022. [find](https://scholar.google.com/scholar?q=P%2E+Soviany%2C+R%2E+T%2E+Ionescu%2C+P%2E+Rota%2C+and+N%2E+Sebe%2C+%E2%80%9CCurriculum+Learning%3A+A+Survey%2C%E2%80%9D+International+Journal+of+Computer+Vision%2C+vol%2E+130%2C+pp%2E+877%E2%80%93+902%2C+2022%2E) 11. X. Wang, Y. Chen, and W. Zhu, “A Survey on Curriculum Learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 9, pp. 4555-4576, 2021. [find](https://scholar.google.com/scholar?q=X%2E+Wang%2C+Y%2E+Chen%2C+and+W%2E+Zhu%2C+%E2%80%9CA+Survey+on+Curriculum+Learning%2C%E2%80%9D+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence%2C+vol%2E+44%2C+no%2E+9%2C+pp%2E+4555%2D4576%2C+2021%2E) *Updated 2 November 2026*