DTBench: A Synthetic Benchmark for Document-to-Table Extraction

arXiv:2602.13812v2 Announce Type: replace Abstract: Document-to-table (Doc2Table) extraction derives structured tables from unstructured documents under a target schema, enabling reliable and verifiable SQL-based data analytics. Although large language models (LLMs) have shown...

🔗 Read more: https://arxiv.org/abs/2602.13812

#News #Chemistry #Software #Policy #AI #Biology #Academic