WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing
WeVisDoc two-stage data framework yields WeVisDoc-4B parser scoring 95.38 on OmniDocBench v1.6 and ranking first across four end-to-end parsing settings.
WeVisDoc is a two-stage data-centric framework for document parsing: Stage I broadens semantic, structural, and appearance coverage via heterogeneous data and structure-preserving degradation synthesis; Stage II uses a held-out probe to diagnose residual errors and guide targeted data construction and token-budget reallocation. WeVisDoc-4B achieves 95.38 Overall on OmniDocBench v1.6 and a mean 75.54 across three PureDocBench tracks, ranking first in all four compared end-to-end settings. Stage II brings larger gains on degraded inputs, including 4.03 points for the 4B model on the Real Degraded track.
- Two-stage framework: broadens coverage with degradation synthesis, then uses probe diagnostics for targeted data construction.
- WeVisDoc-4B scores 95.38 Overall on OmniDocBench v1.6, first among compared end-to-end parsers.
- Mean Overall 75.54 across three PureDocBench tracks; first in all four settings.
- Stage II adds 4.03 points for the 4B model on the Real Degraded track.
Full article174 words · extracted from huggingface.co · click to collapse
Document parsing converts document images into structured content and requires reliable performance across diverse layouts and acquisition conditions. Yet training corpora are biased toward common document types and clean digital pages, while expanding coverage alone does not specify how to address a parser's remaining weaknesses. We present WeVisDoc, a two-stage data-centric framework for robust end-to-end document parsing. Stage I broadens semantic, structural, and appearance coverage through heterogeneous data and structure-preserving degradation synthesis. Stage II uses a held-out probe to measure the Stage I parser's residual errors within fixed visual-structural clusters. These diagnostics guide targeted data construction and reallocation of the target-token budget. WeVisDoc-4B achieves an Overall score of 95.38 on OmniDocBench v1.6 and a mean Overall score of 75.54 across the three PureDocBench tracks, ranking first among the compared end-to-end parsers in all four settings. Compared with Stage I, Stage II improves Overall scores for the 2B and 4B models on both benchmarks, with larger gains on the degraded PureDocBench tracks, including a 4.03-point gain for the 4B model on the Real Degraded track.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.20423