Structured Output
Make the model emit JSON or a table that fits a schema
WHAT THIS CAPABILITY MEANS
Takes natural language plus a target structure — field names, types, required flags — and outputs text that strictly conforms, such as JSON, XML or a table. Unlike information extraction the structure is supplied by the caller rather than inferred from the text; unlike tool use it produces the data itself, not a request to invoke some interface.
How it is done
The basic approach puts the schema and examples in the prompt and asks the model to fill them; more reliable is constrained decoding, which at each step allows only tokens that keep the structure valid, ruling out syntax errors during generation. Fine-tuning on many text-to-structure pairs familiarises the model with common field naming and type conventions. Large schemas can be split across several calls or filled in layers.
Representative products
5GPT-4o
2024A natively multimodal general model, with text, image and audio through one door
Claude
2023A general chat model known for long context and safety alignment
Gemini
2023A natively multimodal general model built for very long context
Qwen
2023An open-weight family spanning many sizes, with multimodal versions
Hunyuan
2023Tencent’s general model family, with open-weight versions
Organizations involved
Typical uses
- Converting natural language into API payloads
- Auto-filling forms and order fields
- Data cleaning and normalisation pipelines
- Passing structured messages between agents
How it is evaluated
- Schema validity rate
- Share of outputs that parse and satisfy the schema
- Field exact match
- Share of field values matching the reference
- Value-level F1
- Scores elements in lists and nested structures
Limits and hard parts
- With many fields or long enums it drops fields, picks the wrong value or invents new ones
- Deep nesting and complex types such as unions or nullable arrays produce type errors
- Tight format constraints squeeze reasoning, and the same model reasons less well under them
Concepts behind it
Prompting & Alignment
Making a model helpful, honest and harmless is harder than simply making it bigger
Transformer Architecture
Replacing word-by-word relay with a room where everyone speaks at once, so long-range dependencies are one hop away
Agents & Tool Use
Let a model do more than answer: search, call APIs, run code — and decide the next step from what came back