@inproceedings{qiao-etal-2025-v,
    title = "{V}-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me",
    author = "Qiao, Runqi  and
      Tan, Qiuna  and
      Dong, Guanting  and
      MinhuiWu, MinhuiWu  and
      Wang, Jiapeng  and
      Zhang, YiFan  and
      GongQue, Zhuoma  and
      Sun, Chong  and
      Xu, Yida  and
      Xue, Yadong  and
      Tian, Ye  and
      Bao, Zhimin  and
      Yang, Lan  and
      Li, Chen  and
      Zhang, Honggang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.986/",
    pages = "20124--20150",
    ISBN = "979-8-89176-251-0",
    abstract = "Oracle Bone Script (OBS) is a vital treasure of human civilization, rich in insights from ancient societies. However, the evolution of written language over millennia complicates its decipherment. In this paper, we propose V-Oracle, an innovative framework that utilizes Large Multi-modal Models (LMMs) for interpreting OBS. V-Oracle applies principles of pictographic character formation and frames the task as a visual question-answering (VQA) problem, establishing a multi-step reasoning chain. It proposes a multi-dimensional data augmentation for synthesizing high-quality OBS samples, and also implements a multi-phase oracle alignment tuning to improve LMMs' visual reasoning capabilities. Moreover, to bridge the evaluation gap in the OBS field, we further introduce Oracle-Bench, a comprehensive benchmark that emphasizes process-oriented assessment and incorporates both standard and out-of-distribution setups for realistic evaluation. Extensive experimental results can demonstrate the effectiveness of our method in providing quantitative analyses and superior deciphering capability."
}