Robust Hierarchical Structures for Agentic Document Analysis
This work proposes SHED, a two-stage workflow for inferring a robust and compact structure that improves F-1 scores by 13%--68% over non-LLM baselines and 9%--15% over expensive LLM-based approaches.
Ruiying Ma, Yi-Ming Lin, Aditya G. Parameswaran
· 0 citations