Chain-of-thought
Chain-of-thought is like asking a student to show their work on a math problem instead of just writing down the answer. By forcing the AI to write out each step of its thinking process, it is much less likely to make a mistake and more likely to get the right result.
Chain-of-thought is a prompting technique that encourages a model to generate a sequence of intermediate reasoning steps before producing a final output. This approach decomposes complex problems into smaller, manageable parts, which significantly improves performance on multi-step reasoning, logic, and arithmetic tasks.
A prompting/decoding technique in which the model generates explicit intermediate reasoning steps before the final answer, improving accuracy on multi-step and arithmetic tasks.
evolution
- 2022-01 · historyChain-of-Thought Prompting
Wei et al. introduce the technique of prompting models to generate intermediate reasoning steps to improve performance on complex tasks.
- 2022-05 · historyZero-Shot CoT
Kojima et al. demonstrate that models can perform reasoning without few-shot examples by simply adding the prompt 'Let's think step by step'.
- 2023-05 · historyTree of Thoughts
Yao et al. generalize CoT by allowing models to explore multiple reasoning paths and backtrack, enabling complex problem-solving.
- 2024-09 · historyOpenAI o1 Series
OpenAI releases models explicitly trained with reinforcement learning to perform extensive internal chain-of-thought processing before outputting a response.