←Back to feed
🧠 AI⚪ Neutral
Terminology Rarity Predicts Catastrophic Failure in LLM Translation of Low-Resource Ancient Languages: Evidence from Ancient Greek
arXiv – CS AI|James L. Zainaldin, Cameron Pattison, Manuela Marai, Jacob Wu, Mark J. Schiefsky||1 views
🤖AI Summary
A study evaluated large language models (Claude, Gemini, ChatGPT) translating Ancient Greek texts, finding high performance on previously translated works (95.2/100) but declining quality on untranslated technical texts (79.9/100). Terminology rarity was identified as a strong predictor of translation failure, with rare terms causing catastrophic performance drops.
Key Takeaways
- →LLMs achieved near-expert translation quality on previously translated Ancient Greek expository texts.
- →Performance significantly declined on untranslated pharmacological texts with dense technical terminology.
- →Terminology rarity showed strong correlation (r = -.97) with translation failure rates.
- →Automated evaluation metrics failed to discriminate among high-quality translations effectively.
- →The study provides insights for using LLMs in classical scholarship and low-resource language translation.
#llm#machine-translation#ancient-languages#ai-research#natural-language-processing#low-resource-languages#translation-quality#terminology#academic-research
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Related Articles