arXiv 2604.112992026-04-13cs.CLcs.AI

通过字形驱动微调增强多模态大语言模型用于古汉字演变分析

Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning

College of Computer Science and Technology, Jilin University, China（吉林大学计算机科学与技术学院）；Key Laboratory of Ancient Chinese Script, Culture Relics and Artificial Intelligence, Jilin University, China（吉林大学古文字、文物与人工智能重点实验室）；School of Artificial Intelligence, Jilin University, China（吉林大学人工智能学院）；School of Archaeology, Jilin University, China（吉林大学考古学院）

Rui Song, Lida Shi, Ruihua Qi, Yingji Li, Hao Xu

备注：: Accepted by ACL 2026 main

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出GEVO框架，通过字形驱动微调提升多模态大语言模型在古汉字演变分析中的能力，实验显示模型在多个任务上均取得显著提升。

摘要：

近年来，多模态大语言模型（MLLMs）的快速发展推动了对古代汉字的研究。作为理解文化变迁和历史连续性的基本途径，如何系统利用MLLMs支持和推进文本演变分析仍是一个开放且研究不足的问题。为此，我们构建了一个包含11个任务和超过13万个实例的综合基准，专门用于评估MLLMs在分析古代汉字演变能力。我们对多个广泛使用的MLLMs进行了广泛评估，发现现有模型在字形级比较方面能力有限，但在核心任务如字符识别和进化推理上的表现仍受到显著限制。受这些发现的启发，我们提出了一个字形驱动的微调框架（GEVO），旨在明确鼓励模型捕捉字形转换中的进化一致性，并增强其对文本演变的理解。实验结果表明，即使在2B规模的模型上，也能在所有评估任务上实现一致且全面的性能提升。为了促进未来研究，我们公开发布了该基准和训练好的模型（https://github.com/songruiecho/GEVO）.

英文摘要：

In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the evolution of written characters constitutes a fundamental pathway for understanding cultural transformation and historical continuity, how MLLMs can be systematically leveraged to support and advance text evolution analysis remains an open and largely underexplored problem. To bridge this gap, we construct a comprehensive benchmark comprising 11 tasks and over 130,000 instances, specifically designed to evaluate the capability of MLLMs in analyzing the evolution of ancient Chinese scripts. We conduct extensive evaluations across multiple widely used MLLMs and observe that, while existing models demonstrate a limited ability in glyph-level comparison, their performance on core tasks-such as character recognition and evolutionary reasoning-remains substantially constrained. Motivated by these findings, we propose a glyph-driven fine-tuning framework (GEVO) that explicitly encourages models to capture evolutionary consistency in glyph transformations and enhances their understanding of text evolution. Experimental results show that even models at the 2B scale achieve consistent and comprehensive performance improvements across all evaluated tasks. To facilitate future research, we publicly release both the benchmark and the trained models\footnote{https://github.com/songruiecho/GEVO}.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。