SOURCE-LINKED INTELLIGENCE

Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

The Mutual Reinforcement Effect (MRE) asks whether a fine, span-level and a coarse, document-level task help each other when one model handles both. We test it in multimodal document understanding on three corpora, two of receipts and one of scanned business forms, comparing single-task, joint and conditioned training, which puts one granularity's gold output in the other's prompt during training only. We build Doc-MRE, an annotation layer pairing gold field extraction (point) with four document-level facets (line), from a three-judge LLM committee under a pre-registration, validated by blind

Read original source ↗ Open in workspace

recordType

paper

region

Global