You have to learn the rules of the game. And then you have to play better than anyone else
- Advanced prompting techniques (e.g., chain of thought and tree of thought) improve the problem-solving capabilities of large language models (LLMs).
- These techniques require LLMs to construct step-by-step responses.
- They assume linear reasoning, which differs from human reasoning involving multiple chains of thought and insights combination.
- This overview focuses on prompting techniques using a graph structure to capture non-linear problem-solving patterns.