AI2-Israel's Yoav Goldberg argues LLM researchers are rebranding established ML concepts with unnecessary reinforcement learning jargon

From: AI2-Israel's Yoav Goldberg argues LLM researchers are rebranding established ML concepts with unnecessary reinforcement learning jargon

(((ل()(ل() 'yoav))))👾@yoavgo·3hReply

@srush_nlp (also i do think it is important to distinguish "policies" where the actions are tokens, from policies where the actions are, say, tool calls or reasoning steps. so i do not think we should abstract over these things..)

View on

AI2-Israel's Yoav Goldberg argues LLM researchers are rebranding established ML concepts with unnecessary reinforcement learning jargon · Digg