Structure-Aware Text Recognition for Ancient Greek Critical Editions
This addresses the challenge of structure-aware text recognition for historical scholarly documents, which is incremental as it builds on existing VLM methods with new datasets and evaluations.
The paper tackled the problem of interpreting complex layout semantics in Ancient Greek critical editions using visual language models, finding that while current models underperform in zero-shot settings, the Qwen3VL-8B model achieved state-of-the-art performance with a median Character Error Rate of 1.0% on real scans.
Recent advances in visual language models (VLMs) have transformed end-to-end document understanding. However, their ability to interpret the complex layout semantics of historical scholarly texts remains limited. This paper investigates structure-aware text recognition for Ancient Greek critical editions, which have dense reference hierarchies and extensive marginal annotations. We introduce two novel resources: (i) a large-scale synthetic corpus of 185,000 page images generated from TEI/XML sources with controlled typographic and layout variation, and (ii) a curated benchmark of real scanned editions spanning more than a century of editorial and typographic practices. Using these datasets, we evaluate three state-of-the-art VLMs under both zero-shot and fine-tuning regimes. Our experiments reveal substantial limitations in current VLM architectures when confronted with highly structured historical documents. In zero-shot settings, most models significantly underperform compared to established off-the-shelf software. Nevertheless, the Qwen3VL-8B model achieves state-of-the-art performance, reaching a median Character Error Rate of 1.0\% on real scans. These results highlight both the current shortcomings and the future potential of VLMs for structure-aware recognition of complex scholarly documents.