Stay updated with breaking news from Language Systems Group. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
A new technique can more effectively perform a safety check on an AI chatbot. MIT researchers enabled their model to prompt a chatbot to generate toxic responses, which are used to prevent the chatbot from giving hateful or harmful answers when deployed.
James Glass is a Senior Research Scientist at MIT, leading the Spoken Language Systems Group at CSAIL. He is also affiliated ...
Automated speech-recognition technology has become more common with the popularity of virtual assistants like Siri, but many of these systems only