3 Comments

Very insightful. The specific dataset used to better reveal higher level reasoning already inherent in LLMs is very interesting. For clarification, is CoAT employing a structured memory graph - and if so, what do the nodes and edges represent?

Expand full comment

Hello- can we say that COAT is extending the prompt stage RAG concept to LLM reasoning ? Thx

Expand full comment

I wanted to say no at first, but there actually is one fundamental similarity between the two: both give the model information it would "usually" not have access to. If that's what you're thinking of, then yes. Other than that they are very different concepts.

Expand full comment