#artificial intelligence
May 2026
Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions
Comparing open-weight VLMs with traditional OCR baselines on low-resource Ancient Greek critical editions, it is shown that VLM errors often remain fluent even when wrong, producing plausible Greek substitutions where traditional engines produce local recognition noise.
Antonia Karamolegkou, Nicolas Angleraud, Benoît Sagot et al.
· arXiv.org · 4 citations