# Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study

arXiv: https://arxiv.org/abs/2605.07453 · HTML: https://mlsanity.com/paper/2605.07453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 11 of 11)

- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [From LLM to NMT: Advancing Low-Resource Machine Translation with Claude](https://mlsanity.com/paper/2404.13813/) (2024)
- [ConStat: Performance-Based Contamination Detection in Large Language Models](https://mlsanity.com/paper/2405.16281/) (2024)
- [Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation](https://mlsanity.com/paper/2501.18771/) (2025)
- [LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP](https://mlsanity.com/paper/2408.04628/) (2024)
- [When Flores Bloomz Wrong: Cross-Direction Contamination in Machine Translation Evaluation](https://mlsanity.com/paper/2601.20858/) (2026)
- [Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora](https://mlsanity.com/paper/2601.14994/) (2026)

## Abstract (arXiv)

Ancient and endangered languages pose a unique challenge for NLP: their datasets are inherently scarce, difficult to expand, and built from formulaic corpora -- making data-quality issues especially consequential yet rarely audited. Motivated by the need to understand what current NMT can realistically achieve for such languages, we investigate hieroglyphic-to-German translation, where a recent study reported 61.5 BLEU using fine-tuned M2M-100. Our reproduction yields only 37.0 BLEU with the released model. Investigating this gap, we find 2% of test targets appear identically in training (16/50; 50% under 8-gram overlap at 70% threshold). This contamination inflates scores dramatically: contaminated samples achieve up to 83.8 BLEU / 0.924 COMET-22 versus 30.9--39.2 BLEU / 0.622--0.676 COMET-22 on clean samples across five model configurations spanning two architectures. Document-level decontamination reduces contaminated BLEU by only 4.6 points because 8/16 targets persist via other source documents -- target-level deduplication is required. We release a decontaminated 34-sample test set and establish corrected baselines (30.9--39.2 BLEU), providing a realistic assessment of NMT capability for this endangered writing system.