Re:How Chain-of-Thought Reasoning Helps Neural Networks Compute
by phailhaus on Friday March 22, 2024 @11:57AM
(#39791942)
> Sure, but why does that make the model more effective?
Because the model can't "think". There is no "reasoning" that goes into generating an answer. So for complex problems that require multiple steps of reasoning, the model needs to persist those intermediate steps in order to be able to build up to a solution.
Because the model can't "think". There is no "reasoning" that goes into generating an answer. So for complex problems that require multiple steps of reasoning, the model needs to persist those intermediate steps in order to be able to build up to a solution.