# Efficient Guided Generation for Large Language Models

*Source* · `src-willard-2023-outlines` · status: **n/a**

| field | value |
|---|---|
| kind | Preprint |
| authors | Brandon T. Willard, Rémi Louf |
| venue | arXiv |
| date | 2023-07-19 |
| url | https://arxiv.org/abs/2307.09702 |
| arxiv | 2307.09702 |
| accessed | 2026-10-24 |

## Notes

Outlines: recasts generation as transitions of a finite-state machine with a precomputed index from states to allowed vocabulary tokens, constraining output to regular expressions and context-free grammars with little overhead.

## Backlinks (computed)

**cited by:** [Grammar-constrained decoding for valid game actions](../technique/constrained-decoding.md)

## Citation

Brandon T. Willard, Rémi Louf (2023-07-19). *Efficient Guided Generation for Large Language Models*. arXiv https://arxiv.org/abs/2307.09702

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.