<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-2026-parameter">
    <titleInfo>
        <title>A Parameter-Efficient and Data-Centric Framework for Ancient Chinese Text Recognition and Layout Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuchun</namePart>
        <namePart type="family">Meng</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>This paper presents the system developed for the EvaHan 2026 shared task on Ancient Chinese OCR and Layout Analysis. Participating in the Closed Track, we propose a highly parameter-efficient, data-centric framework based on the Qwen2.5-VL-7B-Instruct multimodal large language model (MLLM). While the official baseline utilizes the same backbone architecture, our approach significantly outperforms it by integrating orientation-aware image preprocessing and expert-constrained adaptive prompt engineering. We employed Low-Rank Adaptation (LoRA) with a minimal rank configuration (Rank=16) to train three independent, task-specific adapters. Our system achieved exceptional results, recording an Overall score of 0.9703 and an F1-score of 97.19% on printed text recognition (Task A)—effectively halving the baseline’s Character Error Rate. On handwritten texts (Task C), we maintained a highly competitive 90.18% F1-score. Furthermore, our model achieved significant progress in layout analysis (Task B), surpassing the baseline’s Macro F1 by 172% (0.4162 vs. 0.1530) and mAP by 37%. These results underscore that embedding explicit document structure and semantic constraints into MLLMs is more effective than simply scaling model parameters.</abstract>
    <identifier type="citekey">meng-2026-parameter</identifier>
    <identifier type="doi">10.63317/4inrcp772rid</identifier>
    <location>
        <url>https://aclanthology.org/2026.lt4hala-1.29/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>294</start>
            <end>298</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Parameter-Efficient and Data-Centric Framework for Ancient Chinese Text Recognition and Layout Analysis
%A Meng, Yuchun
%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 meng-2026-parameter
%X This paper presents the system developed for the EvaHan 2026 shared task on Ancient Chinese OCR and Layout Analysis. Participating in the Closed Track, we propose a highly parameter-efficient, data-centric framework based on the Qwen2.5-VL-7B-Instruct multimodal large language model (MLLM). While the official baseline utilizes the same backbone architecture, our approach significantly outperforms it by integrating orientation-aware image preprocessing and expert-constrained adaptive prompt engineering. We employed Low-Rank Adaptation (LoRA) with a minimal rank configuration (Rank=16) to train three independent, task-specific adapters. Our system achieved exceptional results, recording an Overall score of 0.9703 and an F1-score of 97.19% on printed text recognition (Task A)—effectively halving the baseline’s Character Error Rate. On handwritten texts (Task C), we maintained a highly competitive 90.18% F1-score. Furthermore, our model achieved significant progress in layout analysis (Task B), surpassing the baseline’s Macro F1 by 172% (0.4162 vs. 0.1530) and mAP by 37%. These results underscore that embedding explicit document structure and semantic constraints into MLLMs is more effective than simply scaling model parameters.
%R 10.63317/4inrcp772rid
%U https://aclanthology.org/2026.lt4hala-1.29/
%U https://doi.org/10.63317/4inrcp772rid
%P 294-298

Markdown (Informal)

[A Parameter-Efficient and Data-Centric Framework for Ancient Chinese Text Recognition and Layout Analysis](https://aclanthology.org/2026.lt4hala-1.29/) (Meng, LT4HALA 2026)

• A Parameter-Efficient and Data-Centric Framework for Ancient Chinese Text Recognition and Layout Analysis (Meng, LT4HALA 2026)

ACL

• Yuchun Meng. 2026. A Parameter-Efficient and Data-Centric Framework for Ancient Chinese Text Recognition and Layout Analysis. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 294–298, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).