A new model improves AI's ability to learn from user feedback.
― 6 min read
Felix Friedrich
AI improves decision-making through self-explanations and feedback loops.
― 7 min read
The impact of language on gender stereotypes in image generation technologies.
― 5 min read
ALERT benchmark assesses safety risks in language models to improve their responses.
― 4 min read
A new system assesses safety risks in images generated by AI models.
― 7 min read
Scar enhances language models by reducing toxic language in text generation.
― 5 min read
This article examines shortcut learning issues in machine learning and how to address them.
― 7 min read
M-ALERT tests language models for safety across five languages.
― 5 min read