Structured Output

Noun · AI & Machine Learning

Definitions

  1. Constraining an LLM's output to conform to a specific format like JSON Schema, XML, or a grammar. Achieved through guided decoding (constraining token probabilities to valid next tokens) or tool use / function calling. Essential for reliable LLM integration into software systems that expect structured data.

    In plain English: Making an AI always respond in a specific format (like valid JSON) instead of free-form text.

    Example: "Use structured output with a JSON schema — the model is guaranteed to return valid JSON matching your interface, no parsing failures."

Related Terms