Skip to content
AI News HubLIVE
Original source2 min read

ParseBench-2: Severity-Aware Evaluation of Document Parsing

Summary

ParseBench-2 introduces a method for developing document-parsing metrics from severity policies, using test scenarios to optimize metric implementations. The benchmark covers 4,317 pages across six parsing-quality dimensions and combines a content-recovery score with a severity cap to prevent high recovery from hiding serious errors. Experiments show the metrics align more closely with expert judgments and penalize at most 3.4% of benign variations, and are used to evaluate frontier vision-language models, specialized parsers, and open-weight systems on rankings, capability performance, and cost tradeoffs.

SourcearXiv Computer VisionAuthor: Pierre-Lo\"ic Doulcet, Boyang Zhang, Sebasti\'an G. Acosta, Sacha Bron, Daniel B. Ospina, Antonio Jimeno Yepes, Nutchapol Dendumrongsup, Simon Suo
ParseBench-2: Severity-Aware Evaluation of Document Parsing
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

Title:ParseBench-2: Severity-Aware Evaluation of Document Parsing

View a PDF of the paper titled ParseBench-2: Severity-Aware Evaluation of Document Parsing, by Pierre-Lo\"ic Doulcet and 7 other authors

View PDF HTML (experimental)

Abstract: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.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.17400 [cs.CV]

(or arXiv:2611.17400v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.17400

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Boyang Zhang [view email] [v1] Thu, 12 Nov 2026 18:54:23 UTC (530 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled ParseBench-2: Severity-Aware Evaluation of Document Parsing, by Pierre-Lo\"ic Doulcet and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Proposes a severity-policy-driven method that turns human priorities into explicit objectives for metric design, using test scenarios and coding agents under human review.
  • ParseBench-2 spans 4,317 pages and six dimensions (text, formatting, tables, charts, visual grounding, forms), with detailed annotations and hard cases to detect changed facts, broken structure, and missing content.
  • Takes the lower of a parsing score and a severity cap so recovering most of a page cannot hide a serious error; metrics better match expert judgments and penalize at most 3.4% of benign variations.
  • Provides a comprehensive evaluation of frontier vision-language models, specialized document parsers, and open-weight systems, comparing overall rankings, per-capability performance, and accuracy-cost tradeoffs.

Highlights and analysis are generated automatically and may contain errors. Check the original source.