Abstract
This article presents an experiment in fine-tuning a pretrained causal language model (Meta's Llama 3.1 8B Instruct) for aiding in three fundamental tasks of philological research: chronological and geographic attribution as well as text restoration in ancient Greek inscriptions and documentary papyri. Using a prompt-based instruct approach, the fine-tuned models surpass the state of the art in key metrics. For inscriptions, the models achieve a lower average character error rate (CER) of 22.5% (vs. 26.3%), while closely matching top-1 accuracy (60.9% vs. 61.8%) and top-20 accuracy (77.5% vs. 78.3%) for sequences up to 10 characters. They also provide a practical advantage by ignoring spaces during reconstruction, aligning better with the scriptio continua typically used in ancient written artifacts. In geographic attribution, the model outperforms previous benchmarks with a top-1 accuracy of 75.0% (vs. 70.8%) and a top-3 accuracy of 83.7% (vs. 82.1%). For dating, it achieves an average deviation of 26.2 years (vs. 29.3) and a median deviation of 1 year (vs. 3) from the actual date range. The models also set new baselines for documentary papyri, with a CER of 16.3%, a top-1 accuracy of 71.3%, and top-20 of 85.0% in text reconstruction; a top-1 accuracy of 66.4% and top-3 of 79.9% in geographic attribution; and, in chronological attribution, a deviation of 21.7 years from the actual termini post/ante quem, with a median deviation of 0 years.
Abstract (translated)
这篇文章介绍了一个实验：对预训练的因果语言模型（Meta的Llama 3.1 8B指令）进行微调，以帮助促进三个基本的文献研究任务：chronological和geographic attribution，以及古希腊铭文和文书手稿的文字修复。通过一种基于提示的指令方法，微调后的模型在关键指标上超越了最先进的水平。对于铭文，模型实现了22.5%的平均字符错误率（CER）（相对于26.3%），同时对于Top 1准确度（60.9%相对于61.8%）和Top 20准确度（77.5%相对于78.3%）也具有优势。它们还通过在重建过程中忽略空格来提供实际优势，与古代书面文献中通常使用的脚本更接近。在地理归因方面，该模型在Top 1准确度为75.0%（相对于70.8%）和Top 3准确度为83.7%（相对于82.1%）的基准测试中超过了最先进水平。对于日期，它实现了26.2年的平均偏差（相对于29.3%）和1年的中位数偏差（相对于3），以及对于文书手稿的新的基线。这些模型还设定了新的文档手稿基线，具有16.3%的CER，文本重建的Top 1准确度为71.3%，Top 20准确度为85.0%；地理归因的Top 1准确度为66.4%，Top 3准确度为79.9%；在chronological attribution方面，偏差为21.7年，中位偏差为0年。
URL
https://arxiv.org/abs/2409.13870
