Papers
arxiv:2611.17400

ParseBench-2: Severity-Aware Evaluation of Document Parsing

Published on Nov 12
Authors:
,
,
,
,
,
,
,

Abstract

A method for deriving document-parsing metrics from human severity policies produces a benchmark whose metrics align more closely with expert judgments and penalize few benign variations while evaluating vision-language and document parsing systems.

Document-parsing metrics can give high scores to outputs that change important facts and penalize changes that preserve meaning. People can often judge these consequences more easily than they can design a metric to measure them. We introduce a method for developing parsing metrics from severity policies that specify how each error type should affect the score. We express these policies through test scenarios that specify how a metric should behave. We then optimize the metric implementations against these fixed expectations, using coding agents to refine comparison rules, error detectors and weights under human review. This makes stated human priorities an explicit objective of metric design. We apply this method in ParseBench-2, a comprehensive document-parsing benchmark that combines broad capability coverage with metrics calibrated to error severity. It covers 4,317 pages across six dimensions of parsing quality: text, formatting, tables, charts, visual grounding, and forms. We use detailed annotations and targeted difficult cases to check for changed facts, broken structural relationships, and missing content. We take the lower of a parsing score that measures content recovery and a severity cap that penalizes detected errors, so recovering most of a page cannot hide a serious error. Across six severity test suites, our metrics more closely match the expert judgments expressed by the scenario targets than existing metrics and penalize at most 3.4% of the tested benign variations. We conduct a comprehensive evaluation spanning frontier vision-language models, specialized document parsers and open-weight systems, comparing their overall rankings, performance across parsing capabilities and tradeoffs between accuracy and cost.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.17400
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.17400 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.17400 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.17400 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.