How language models like ChatGPT learn new tasks from just a few examples scienceblog.com - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from scienceblog.com Daily Mail and Mail on Sunday newspapers.
MIT researchers have explained how large language models like GPT-3 are able to learn new tasks without updating their parameters, despite not being trained to perform those tasks. They found that these large language models write smaller linear models inside their hidden layers, which the large models can train to complete a new task using simple learning algorithms.
Sometimes, machine learning models learn a new task without seeming to have learned – or been trained – to do it. That’s the findings of researchers at [.]