Do LLMs Really Think Step-by-step In Implicit Reasoning? — mentioned by layoric

Thu, 22 May 2025 22:37:19 GMT

There are several papers pointing towards 'thinking' output is meaningless to the final output, and using dots, or pause tokens enabling the same additional rounds of throughput result in similar improvements. So in a lot of regards the 'thinking' is mostly marketing. - "Think before you speak: Training Language Models With Pause Tokens" - https://arxiv.org/abs/2310.02226 - "Let's Think Dot by Dot: Hidden Computation in Transformer Language Models" - https://arxiv.org/abs/2404.15758 - "Do LLMs Really Think Step-by-step In Implicit Reasoning?" - https://arxiv.org/abs/2411.15862 - Video by…

Paper and discussion history. A mention is not an endorsement.

Do LLMs Really Think Step-by-step In Implicit Reasoning? · HackerPapers discussions

Do LLMs Really Think Step-by-step In Implicit Reasoning? — mentioned by layoric