"What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs

Documenti analoghi

• ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images
  di: Sibue, Mathieu, et al.
  Pubblicazione: (2026)
• BuDDIE: A Business Document Dataset for Multi-task Information Extraction
  di: Zmigrod, Ran, et al.
  Pubblicazione: (2024)
• TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing
  di: Zmigrod, Ran, et al.
  Pubblicazione: (2024)
• DocLLM: A layout-aware generative language model for multimodal document understanding
  di: Wang, Dongsheng, et al.
  Pubblicazione: (2023)
• CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation
  di: S, Santosh T. Y. S., et al.
  Pubblicazione: (2025)