Integrating Machine-Generated Short Descriptions into the Wikipedia Android App: A Pilot Deployment of Descartes

TL;DR

This paper reports on a pilot deployment of Descartes, a multilingual machine-generated short description system integrated into the Wikipedia Android app, showing promising quality and editor acceptance across 12 languages.

Contribution

It demonstrates the practical deployment and evaluation of Descartes in a real-world setting, highlighting its effectiveness and challenges in supporting Wikipedia editors.

Findings

90% of Descartes suggestions rated at least 3/5 in quality

Editors adopted machine suggestions with modifications

Low revert and report rates indicate acceptance and safety

Abstract

Short descriptions are a key part of the Wikipedia user experience, but their coverage remains uneven across languages and topics. In previous work, we introduced Descartes, a multilingual model for generating short descriptions. In this report, we present the results of a pilot deployment of Descartes in the Wikipedia Android app, where editors were offered suggestions based on outputs from Descartes while editing short descriptions. The experiment spanned 12 languages, with over 3,900 articles and 375 editors participating. Overall, 90% of accepted Descartes descriptions were rated at least 3 out of 5 in quality, and their average ratings were comparable to human-written ones. Editors adopted machine suggestions both directly and with modifications, while the rate of reverts and reports remained low. The pilot also revealed practical considerations for deployment, including latency, language-specific gaps, and the need for safeguards around sensitive topics. These results indicate that Descartes's short descriptions can support editors in reducing content gaps, provided that technical, design, and community guardrails are in place.