DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents
Quick summary
arXiv:2609.24092v1 Announce Type: new Abstract: Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page. Extracting these implicit values requires multi-hop derivation, such as aggregating sub-categories or reasoning over visual marks. While existing methods handle explicit text spans or simple implicit queries, they fail at multi-hop visual reasoning even after standard fine-tuning: models retrieve incorrect visual evidence, or retrieve it correctly and then skip the intermediate steps of the deriva
Key takeaways
- arXiv:2609.24092v1 Announce Type: new Abstract: Real-world document processing systems rely on rigid, predefined schemas, yet critical target fields often lack direct visual counterparts on the page.
- Extracting these implicit values requires multi-hop derivation, such as aggregating sub-categories or reasoning over visual marks.
- While existing methods handle explicit text spans or simple implicit queries, they fail at multi-hop visual reasoning even after standard fine-tuning: models retrieve incorrect visual evidence, or retrieve it correctly and then skip the intermediate steps of the deriva
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments