# An Annotated Dataset of Errors in Premodern Greek and Baselines for Detecting Them

arXiv: https://arxiv.org/abs/2410.11071 · HTML: https://mlsanity.com/paper/2410.11071/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Should You Mask 15% in Masked Language Modeling?](https://mlsanity.com/paper/2202.08005/) (2022)
- [BERT in Plutarch's Shadows](https://mlsanity.com/paper/2211.05673/) (2022)
- [Instruct-Tuning Pretrained Causal Language Models for Ancient Greek Papyrology and Epigraphy](https://mlsanity.com/paper/2409.13870/) (2024)
- [Fast-ELECTRA for Efficient Pre-training](https://mlsanity.com/paper/2310.07347/) (2023)
- [Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach](https://mlsanity.com/paper/2403.06682/) (2024)

## Built on by (most cited first, 1 of 1)

- [Apollo Restore: A Foundation LLM for Historical Greek Optimized for Fill-in-the-Middle Restoration of Ancient Greek Texts](https://mlsanity.com/paper/2609.22455/) (2026)

## Abstract (arXiv)

As premodern texts are passed down over centuries, errors inevitably accrue. These errors can be challenging to identify, as some have survived undetected for so long precisely because they are so elusive. While prior work has evaluated error detection methods on artificially-generated errors, we introduce the first dataset of real errors in premodern Greek, enabling the evaluation of error detection methods on errors that genuinely accumulated at some stage in the centuries-long copying process. To create this dataset, we use metrics derived from BERT conditionals to sample 1,000 words more likely to contain errors, which are then annotated and labeled by a domain expert as errors or not. We then propose and evaluate new error detection methods and find that our discriminator-based detector outperforms all other methods, improving the true positive rate for classifying real errors by 5%. We additionally observe that scribal errors are more difficult to detect than print or digitization errors. Our dataset enables the evaluation of error detection methods on real errors in premodern texts for the first time, providing a benchmark for developing more effective error detection algorithms to assist scholars in restoring premodern works.