Work

LVLM Optimization for Ancient Chinese Book Image Analysis with Task-specific Augmentation and Instruction Tuning

Year: 2026

Type: conference-paper

Abstract: Ancient Chinese text digitization faces challenges like variant characters and complex layouts.Based on the EvaHan 2026 tasks, this study proposes an LVLM-based framework for printed/handwritten text recognition and layout analysis.To effectively adapt the Qwen2.5-VL-7B-Instructmodel, our methodology innovates through a dual-level optimization strategy: distinct augmentation strategies are developed for OCR and layout tasks, while task-specific prompt templates are engineered to decouple text transcription from coordinate prediction.This combined approach significantly enhances overall task proficiency, achieving Character Error Rates of 0.0372 (printed) and 0.0823 (handwritten), alongside a mean average Precision of 0.2933 for layout analysis.Results show general LVLMs underperform in zero-shot ancient text tasks, but fine-tuning with tailored strategies significantly boosts performance and highlights their potential.

Source: Language Resources and Evaluation Conference (LREC)

DOI: 10.63317/3w5rwjqr49n7

Authors: Tian Xia, Yulong Liu, Yilin Wang, Yumeng Yang, Dongheng Cai, Yuyang Tan, Menghui Yang

Institutions: Renmin University of China, Washington University in St. Louis

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166539980

FWCI:

Cites:

Cited by:

Related to: 10