Skip to content
AImpact
IT EN
Inference Beginner Also known as: CoT · Catena di ragionamento

Chain-of-thought

A technique where the model is asked to spell out the intermediate reasoning steps before giving the final answer, improving accuracy on complex tasks.

ShareLinkedInX

In practice

Adding 'think step by step' to the prompt really works on math, logic, and analysis. Reasoning models (o1, Claude with thinking) do it automatically. It costs more tokens, so use it only where you need it.

Related terms

Reasoning model Few-shot learning

Seen in the wild

7 entries mentioning it
  1. Kimi VL Thinking (Moonshot AI): first open visual model with RL-trained chain-of-thought reasoning
    High
  2. Gemini 2.0 Flash Thinking: multimodal reasoning with visual chain-of-thought
    High
  3. Kimi k1.5: the Chinese competitor to OpenAI o1 with 128k context and long-thinking
    High
  4. Sleeper Agents (Anthropic): backdoored models survive safety training
    High
  5. Tree of Thoughts: the LLM that reasons by exploring alternative branches
    High
  6. Flan-T5 and Flan-PaLM: instruction tuning scales to 1,800 tasks
    High
  7. PaLM 540B: Google's GPT-3 answer brings chain-of-thought
    Medium
← All terms