Chain of Thought
Prompting a model to reason step by step before answering.
Visão geral
Chain of thought asks a model to produce intermediate reasoning before its conclusion, which measurably improves accuracy on problems that need several steps. It solves the problem that a model answering immediately has to reach the answer in one forward pass, with no room to work. It exists because it costs only tokens and needs no training, and it is the clearest case where how a model is asked changes what it can do.
Grafo de tecnologias
Como Chain of Thought se liga ao resto do stack.
Usa e depende de
- Self-Consistency technique Prompting Self-Consistency based on Chain of Thought High ✓ source
- Tree of Thoughts technique Prompting Tree of Thoughts based on Chain of Thought High ✓ source
Usado por
Aplicado a
- Prompt Engineering technique Prompting Chain of Thought used for Prompt Engineering High ✓ source
- Reinforcement Learning concept Algorithms Chain of Thought used for Reinforcement Learning Medium ✓ source
- GSM8K benchmark Benchmarks Chain of Thought solves GSM8K High ✓ source