A curated list of structured generation resources
| Name | Description | Author |
|---|---|---|
| Outlines | Framework for structured text generation | Dottxt |
| Guidance | Framework for structured text generation | Guidance AI |
| LLGuidance | Guidance for structured AI outputs | Guidance AI |
| LM Format Enforcer | Enforces structured output formatting | Noam Gat |
| XGrammar | AI grammar enforcement for structured outputs | MLC |
| Llama.cpp Grammars | Grammar-based structured output for Llama | Gabor Gereb |
| Title | Description | Author | Date |
|---|---|---|---|
| Coalescence: Structured Text Generation | Blog post about structured text generation approaches | Will Kurt | 2024-02-02 |
| Improving Prompt Consistency with Structured Generations | Improving prompt consistency with structured generations | Hugging Face | 2024-04-30 |
| Structured Output Strategies | Overview of different structured output techniques | Paul Simmering | 2024-05-11 |
| Say What You Mean | Guide to clear structured output design | Will Kurt | 2024-11-20 |
| Introducing Structured Outputs | Introduction to Cohere's structured output capabilities | Cohere | 2024-07-19 |
| Structured Outputs in OpenAI API | Guide to using structured outputs in OpenAI's API | OpenAI | 2024-08-06 |
| Gemini API for Structured Outputs | Documentation for structured outputs in Gemini API | 2024-12-11 | |
| Structured Generation for LLM-as-a-Judge Evaluations | Structured generation for LLM-as-a-Judge evaluations | Caleb Kaiser | 2024-11-27 |
| Title | Authors | Year |
|---|---|---|
| A General-Purpose Algorithm for Constrained Sequential Inference | Daniel Deutsch, Shyam Upadhyay, Dan Roth | 2019 |
| Validating Large Language Models with ReLM | Michael Kuchnik, Virginia Smith, George Amvrosiadis | 2022 |
| Efficient Guided Generation for Large Language Models | Brandon T. Willard, Rémi Louf | 2023 |
| Automata-based constraints for language model decoding | Terry Koo, Frederick Liu, Luheng He | 2024 |
| Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models | Zhi Rui Tam, Cheng-Kuang Wu, Yi-Lin Tsai, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen | 2024 |
| XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models | Yixin Dong, Charlie F. Ruan, Yaxing Cai, Ruihang Lai, Ziyi Xu, Yilong Zhao, Tianqi Chen | 2024 |
| Title | Presenter | Duration | Date |
|---|---|---|---|
| Introduction to Structured Generation | Remi Louf | 15 min | 2024-08-14 |
| Making AI coding assistants better, even for your weird DSLs | George Fahmy | 22 min | 2025-03-03 |
| Structured Generation | Remi Louf | 15 min | 2024-08-14 |
| OpenAI Introduces Structured Outputs in the API (Tutorial) | Elvis Saravia | 15 min | 2024-08-06 |
| Name | Description |
|---|---|
| OpenAI Prompt Guide | Guide to designing effective prompts. |
| Firecrawl | AI-powered prompt engineering tool. |
| UiForm | Prompt engineering with reasoning fields using the JSON Schema |
| Pydantic AI | AI-assisted validation using Pydantic. |
| Unstructured.io | Framework for unstructured data parsing. |
| Name | Institution | Year |
|---|---|---|
| Gorilla | UC Berkeley | 2023 |
| NuExtract | Numind | 2024 |
| Name | Description | Author |
|---|---|---|
| JSON Schema Bench | Benchmarking JSON schema-based datasets. | Guidance AI |
| Kleister Charity | NLP dataset for document understanding. | Applica AI |
| Kleister NDA | NLP dataset for non-disclosure agreements. | Applica AI |
| RealKIE | Key information extraction dataset. | Indico Data Solutions |
| Name | Description | Author |
|---|---|---|
| OpenAI Structured Outputs Samples | OpenAI Structured Outputs Samples | OpenAI |
| Structured outputs | Structured outputs in Ollama | Ollama |
| UiForm Playground | Playground for document analysis with structured generation | UiForm |