Solon Barocas

4 papers Microsoft Research; Cornell University

• Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming
• Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
• Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
• Validating LLM-as-a-Judge Systems under Rating Indeterminacy