A coarse-to-fine LLM framework for document-level numerical semantic matching achieves about 90% F1 on financial disclosure documents, outperforming the prior AutoCheck system by roughly ten points.
Cracking tabular pre- sentation diversity for automatic cross-checking over numerical facts,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Document-Level Tabular Numerical Cross-Checking: A Coarse-to-Fine Approach
A coarse-to-fine LLM framework for document-level numerical semantic matching achieves about 90% F1 on financial disclosure documents, outperforming the prior AutoCheck system by roughly ten points.