Problem
Research questions and friction points this paper is trying to address.
Document Understanding
Cost-Quality Gap
Regulated Industries
Visual-Language Models
Data Curation
Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics
๐ค AI Summary
ๆฌๆๆๅบไธ็งๅบไบๆททๅไธๅฎถ่ง่ง่ฏญ่จๆจกๅ็ๆๆกฃ็่งฃ็ณป็ป๏ผ้่ฟ้พๅบฆๆ็ฅ็ๆฐๆฎๆด็ๅ่ดจ้่ฐๆด็ๆๆฌๅๆๆนๆณ๏ผๆๆ้ไฝไบๅ็็ฎก่กไธๆๆกฃๅค็ๆๆฌใ
๐ Abstract
Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a fraction of workflows, privacy rules preclude external models, and existing open-source VLMs that clear quality thresholds cost more to serve than human annotation. We present a deployed document-understanding system built on a Mixture-of-Experts VLM (35B total, 3B active), fine-tuned on in-house production data mixed with open-domain documents curated by a Difficulty-Aware pipeline for layout diversity, fact-extractability, and cross-model consistency. Fitting on a single H100 and serving heterogeneous workflows via prompting, the model leads all deployable (non-reasoning) baselines up to an order of magnitude larger. A quality-adjusted cost analysis, with confirmation and correction costs calibrated from production telemetry, shows it reduces expected costs by over 80% against the human baseline and by more than 50% against the best competing open-source model, while larger baselines remain economically unviable.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Difficulty-Aware Data Curation
Quality-Adjusted Deployment Economics
Mixture-of-Experts VLM
๐ Similar Papers
No similar papers found.
