Data Science 21 May 2024Unveiling the Criticality of Red Teaming for Generative AI Governance As generative artificial intelligence (AI) systems become increasingly ubiquitous, their potential impact on society amplifies. These advanced language models possess…
Applications 20 March 2024Red Teaming Language Models with Language Models In ours recent paper, we show that it is possible to automatically find inputs that cause harmful text from language…