When Ye was still an undergraduate at Peking University, he and his colleagues modeled the behavior of transformers(opens a new tab) with and without chain-of-thought prompting. Their proof, using another branch of computer science called circuit complexity theory, established how chain-of-thought prompting essentially turns a large problem into a sequence of smaller problems, making it possible for transformers to tackle more complex compositional tasks. “That means … it can solve some problems that lie in a wider or more difficult computational class,” Ye said.
You are viewing a single comment's thread from: