Higher-dimensional bias in a BERT-based disinformation classifier

Algoprudence number

AA:2023:01

Summary advice

The advice commission believes there is a low risk of (higher-dimensional) proxy discrimination by the BERT-based disinformation classifier and that the particular difference in treatment identified by the quantitative bias scan can be justified, if certain conditions apply.

Source of case

Applying our self-build unsupervised bias detection tool on a self-trained BERT-based disinformation classifier on the Twitter1516 dataset. Learn more on Github.

Stanford’s AI Audit Challenge 2023

This case study, in combination with our bias detection tool, has been selected as a finalist for Stanford’s AI Audit Challenge 2023.

Stanford University

Presentation

A visual presentation of this case study can be found in this slide deck.

Report

Dowload the full report and problem statement here.

Normative advice commission

  • Anne Meuwese, Professor in Public Law & AI at Leiden University
  • Hinda Haned, Professor in Responsible Data Science at University of Amsterdam
  • Raphaële Xenidis, Associate Professor in EU law at Sciences Po Paris
  • Aileen Nielsen, Fellow Law&Tech at ETH Zürich
  • Carlos Hernández-Echevarría, Assistant Director and Head of Public Policy at the anti-disinformation nonprofit fact-checker Maldita.es
  • Ellen Judson, Head of CASM and Sophia Knight, Researcher, CASM at Britain’s leading cross-party think tank Demos

Funded by


European Artificial Intelligence & Society Fund

Funding for further development

01-12-2023 funding open source AI auditing tool
Description

SIDN Fund is supporting Algorithm Audit for further development of the bias detection tool. On 01-01-2024, a team has started that is further developing a testing the tool.

Finalist selection Stanford's AI Audit Challenge 2023

28-04-2023 finalist
Description

Our bias detection tool and this case study have been selected as a finalist for Stanford’s AI Audit Challenge 2023.

React to this normative judgement

Your reaction will be sent to the team maintaining algoprudence. A team will review your response and, if it complies with the guidelines, it will be placed in the Discussion & debate section above.

* required

Newsletter

Stay up to date about our work by signing up for our newsletter

Newsletter

Stay up to date about our work by signing up for our newsletter