@inproceedings{zhang-etal-2026-multi-modal,
title = "A Multi-Modal Recognition Framework for Ancient Books Integrating {D}o{RA}-{DPO} Text Recognition and {YOLO} Layout Analysis",
author = "Zhang, Chaokun and
Wen, Xin and
Zhou, Tongtong",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.25/",
doi = "10.63317/58pv4t9t8hmt",
pages = "268--272",
abstract = "The digitization and intelligent analysis of ancient Chinese documents face significant challenges due to diverse scripts, complex layouts, and the prevalence of rare characters. We present a comprehensive multi-modal recognition framework developed for the closed-modality track of the EvaHan 2026 Ancient Chinese Document Multi-Modal Recognition Shared Task. Our approach integrates two specialized pipelines to address these complexities. For text recognition (Tasks A and C), we propose a high-precision OCR system based on the domain-adapted Xunzi{\_}Qwen2{\_}VL{\_}7B{\_}Instruct, leveraging DoRA within a two-stage progressive curriculum learning strategy. To further refine character accuracy, DPO is incorporated alongside a dual-adapter architecture for rare character error localization and correction. For layout detection (Task B), we implement DocLayout-YOLO, enhanced by domain-specific pre-training and Mosaic augmentation to achieve efficient NMS-free element detection. Furthermore, a multi-round robust inference strategy, featuring automatic retry mechanisms and multi-prompt brute-force search, is introduced to handle stubborn and degraded samples effectively. Experimental results demonstrate that our proposed framework achieves superior performance across all evaluation metrics, highlighting its robustness and effectiveness in the digital preservation of ancient Chinese heritage."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-multi-modal">
<titleInfo>
<title>A Multi-Modal Recognition Framework for Ancient Books Integrating DoRA-DPO Text Recognition and YOLO Layout Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaokun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tongtong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The digitization and intelligent analysis of ancient Chinese documents face significant challenges due to diverse scripts, complex layouts, and the prevalence of rare characters. We present a comprehensive multi-modal recognition framework developed for the closed-modality track of the EvaHan 2026 Ancient Chinese Document Multi-Modal Recognition Shared Task. Our approach integrates two specialized pipelines to address these complexities. For text recognition (Tasks A and C), we propose a high-precision OCR system based on the domain-adapted Xunzi_Qwen2_VL_7B_Instruct, leveraging DoRA within a two-stage progressive curriculum learning strategy. To further refine character accuracy, DPO is incorporated alongside a dual-adapter architecture for rare character error localization and correction. For layout detection (Task B), we implement DocLayout-YOLO, enhanced by domain-specific pre-training and Mosaic augmentation to achieve efficient NMS-free element detection. Furthermore, a multi-round robust inference strategy, featuring automatic retry mechanisms and multi-prompt brute-force search, is introduced to handle stubborn and degraded samples effectively. Experimental results demonstrate that our proposed framework achieves superior performance across all evaluation metrics, highlighting its robustness and effectiveness in the digital preservation of ancient Chinese heritage.</abstract>
<identifier type="citekey">zhang-etal-2026-multi-modal</identifier>
<identifier type="doi">10.63317/58pv4t9t8hmt</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.25/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>268</start>
<end>272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Modal Recognition Framework for Ancient Books Integrating DoRA-DPO Text Recognition and YOLO Layout Analysis
%A Zhang, Chaokun
%A Wen, Xin
%A Zhou, Tongtong
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F zhang-etal-2026-multi-modal
%X The digitization and intelligent analysis of ancient Chinese documents face significant challenges due to diverse scripts, complex layouts, and the prevalence of rare characters. We present a comprehensive multi-modal recognition framework developed for the closed-modality track of the EvaHan 2026 Ancient Chinese Document Multi-Modal Recognition Shared Task. Our approach integrates two specialized pipelines to address these complexities. For text recognition (Tasks A and C), we propose a high-precision OCR system based on the domain-adapted Xunzi_Qwen2_VL_7B_Instruct, leveraging DoRA within a two-stage progressive curriculum learning strategy. To further refine character accuracy, DPO is incorporated alongside a dual-adapter architecture for rare character error localization and correction. For layout detection (Task B), we implement DocLayout-YOLO, enhanced by domain-specific pre-training and Mosaic augmentation to achieve efficient NMS-free element detection. Furthermore, a multi-round robust inference strategy, featuring automatic retry mechanisms and multi-prompt brute-force search, is introduced to handle stubborn and degraded samples effectively. Experimental results demonstrate that our proposed framework achieves superior performance across all evaluation metrics, highlighting its robustness and effectiveness in the digital preservation of ancient Chinese heritage.
%R 10.63317/58pv4t9t8hmt
%U https://aclanthology.org/2026.lt4hala-1.25/
%U https://doi.org/10.63317/58pv4t9t8hmt
%P 268-272
Markdown (Informal)
[A Multi-Modal Recognition Framework for Ancient Books Integrating DoRA-DPO Text Recognition and YOLO Layout Analysis](https://aclanthology.org/2026.lt4hala-1.25/) (Zhang et al., LT4HALA 2026)
ACL