Papers for

insurance claims processors

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Vision language model improves multi-step data extraction from complex documents

DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents

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 derivation. To address this, we introduce DocMIDE, a fine-tuning framework that trains compact vision-language models to retrieve visual evidence explicitly before deriving an answer. DocMIDE constrains generation to a plan-retrieve-derive structure and optimizes it with Group Relative Policy Optimization under a four-component, rule-based reward that scores output format, the retrieved evidence block, every intermediate derivation step, and the final value against a verified reference trace. On a 4,151-pair implicit extraction benchmark, DocMIDE raises accuracy from 70.8% to 95.9% on Qwen3.5-4B from only a small set of annotated examples, and transfers to a second backbone architecture. Supervised demonstrations alone do not close this gap at any budget we tested; rewarding the intermediate steps is what does.

Mon 21 SeptArtificial Intelligence
The gist
Many important facts in documents don’t appear directly on the page and need several reasoning steps to figure out. The authors found that existing AI models tend to either pick the wrong clues or skip steps when trying to answer these tricky questions. Their new method, DocMIDE, teaches models to carefully plan, find visual clues, and then make the final decision. This approach greatly improves accuracy in figuring out hidden information from documents, even with a small amount of training data.
Open 2609.24092v1