The Algorithmic Fairness Across Alignment Procedures and Agentic Systems (AFAA) workshop aims to spark discussions on rethinking fairness in AI alignment procedures and agentic system development.

Disaggregated evaluation across subgroups is critical for assessing the fairness of machine learning models, but its uncritical use can mislead practitioners. We show that equal performance across sub...

GSK Careers is hiring a AI/ML Engineer, Responsible AI in London, United Kingdom. Review all of the job details and apply today!

We have an opportunity to build systems that don’t just replicate our current inequities. Will we take them?

State-of-the-art machine learning models are often tested on their ability to generalize materials deemed ’dissimilar’ to training data, but such definitions frequently rely on heuristics. Here, an an...

Machine Learning from Human Preferences

ALT: a greeting card that says happy new year on it

ALT: a woman in a blue dress is standing in front of a bed with an alarm clock on the nightstand that says 4:20