Patrick Schramowski

ALERT benchmark assesses safety risks in language models to improve their responses.

2025-08-21T19:15:48+00:00 ― 4 min read

A new system assesses safety risks in images generated by AI models.

2025-07-31T23:59:00+00:00 ― 7 min read

A new method improves efficiency in language processing by simplifying tokenization.

2025-07-23T09:31:48+00:00 ― 5 min read

Scar enhances language models by reducing toxic language in text generation.

2025-05-25T19:01:12+00:00 ― 5 min read

M-ALERT tests language models for safety across five languages.

2025-02-12T21:58:30+00:00 ― 5 min read