Journal article · 2025 · Open access
Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions
Digital Scholarship in the Humanities, 41(1), 69–76 · Published 25 November 2025 · DOI 10.1093/llc/fqaf131
In brief
“Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions” is a 2025 journal article by Eric Cullhed, published in Digital Scholarship in the Humanities. OpenAlex counts 10 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at Digital Scholarship in the Humanities.
- Citations
- 10
- Most cited in
- 2026 (7)
- Field-weighted impact
- 2.20
- References
- 12
- Authors
- 1
Abstract
This article presents an experiment in fine-tuning Meta’s Llama 3.1 8B Instruct model to restore missing characters in ancient Greek inscriptions and documentary papyri. For papyri, the restoration model achieved a character error rate of 14.9 per cent, top-1 accuracy of 73.5 per cent, and top-20 accuracy of 86.0 per cent for sequences up to 10 characters. Geographic attribution reached 66.4 per cent accuracy (top-3: 79.9 per cent); chronological attribution showed a mean deviation of 21.7 years from actual dates (median: 0 years). For inscriptions, restoration achieved 20.5 per cent CER, 63.7 per cent top-1 accuracy, and 83.0 per cent top-20 accuracy. Geographic attribution reached 75.0 per cent accuracy (top-3: 83.7 per cent); dating showed a mean deviation of 37.1 years (median: 3 years). When benchmarked against Ithaca on a shared test set as well as recently edited inscriptions, the instruction-tuned models excelled in text restoration while naturally handling scriptio continua. However, geographic and chronological attribution performance was lower than Ithaca’s. When retrained with Ithaca’s 80/10/10 data split, the model still outperformed Ithaca in restoration, even on the test set with recently edited inscriptions. Although comparisons to previous models should be treated with caution—since, due to the pretraining of Llama, they were not trained on identical datasets—the results suggest that fine-tuning large pretrained language models using instruction templates holds significant promise for ancient text restoration.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Cullhed, E. (2025). Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions. Digital Scholarship in the Humanities, 41(1), 69–76. https://doi.org/10.1093/llc/fqaf131
MLA 9
Cullhed, Eric. “Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions.” Digital Scholarship in the Humanities, vol. 41, no. 1, 2025, pp. 69–76. https://doi.org/10.1093/llc/fqaf131.
Chicago
Cullhed, Eric. 2025. “Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions.” Digital Scholarship in the Humanities 41 (1): 69–76. https://doi.org/10.1093/llc/fqaf131.
Harvard
Cullhed, E. (2025) ‘Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions’, Digital Scholarship in the Humanities, 41(1), pp. 69–76. doi:10.1093/llc/fqaf131.
IEEE
E. Cullhed, “Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions,” Digital Scholarship in the Humanities, vol. 41, no. 1, pp. 69–76, 2025, doi: 10.1093/llc/fqaf131.
BibTeX
@article{cullhed2025instruction,
title = {{Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions}},
author = {Cullhed, Eric},
journal = {Digital Scholarship in the Humanities},
year = {2025},
volume = {41},
number = {1},
pages = {69--76},
doi = {10.1093/llc/fqaf131},
url = {https://doi.org/10.1093/llc/fqaf131}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 2 | |
| 2026 | 7 |
Its field-weighted citation impact is 2.20: it has been cited 2.20 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- ancient Greek inscriptions
- papyri
- textual restoration
- instruction tuning
- Llama 3.1
- causal language models
- Ithaca
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Cullhed, E. (2025). Instruction-tuning pretrained causal language models to restore ancient Greek papyri and inscriptions. Digital Scholarship in the Humanities, 41(1), 69–76. https://doi.org/10.1093/llc/fqaf131
How many times has this paper been cited?
10 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Digital Scholarship in the Humanities: sign in and open the PDF from this page.
Who wrote this paper?
Eric Cullhed.
What is the DOI of this paper?
10.1093/llc/fqaf131, permanently at https://doi.org/10.1093/llc/fqaf131. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.