Preprint
Jul 2026
Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis
SAYRE is presented, a scene-aware document synthesis framework for generating scalable KIE training data without hand-crafted template design, and error analysis shows that synthesized training reduces field-level errors by improving schema-aware extraction over dense tables, business identifiers, and contract clauses.
Zhipeng Xu, Zulong Chen, Qing Liu et al.
· 0 citations