Structured Outputs
Also called JSON mode, constrained decoding, schema-constrained generation.
Structured outputs constrain a language model to produce responses that conform to a specified format, typically a JSON Schema, either through instructions or through constrained decoding that guarantees validity.
Description
Instruction-only approaches can still produce malformed output, while constrained decoding masks tokens that would violate the schema at each step. Structured outputs are essential for passing model results reliably to downstream code.
Sources
- OpenAI (2024). Structured model outputs.
- Willard & Louf (2023). Efficient Guided Generation for Large Language Models.
Cite this entry
Protologue. (2026). Structured Outputs. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0062). https://protologue.com/t/structured-outputs/
BibTeX
@misc{protologue_structured_outputs,
title = {Structured Outputs},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0062},
url = {https://protologue.com/t/structured-outputs/}
}