# Greedy Decoding

> Greedy decoding generates text by always choosing the single most probable next token, which makes output deterministic for a given prompt and model.

- Identifier: PTL-0109
- Category: Foundations
- Canonical URL: https://protologue.com/t/greedy-decoding/
- Also known as: argmax decoding, temperature 0

## Description

It is the limit of sampling as temperature approaches zero and is often used when consistency matters, as in extraction or classification. For open-ended text it tends to produce bland or repetitive output, and for reasoning tasks sampling several answers and voting, as in self-consistency, usually beats a single greedy answer.

## Related terms

- [Temperature](https://protologue.com/t/temperature/)
- [Top-k Sampling](https://protologue.com/t/top-k-sampling/)
- [Top-p Sampling](https://protologue.com/t/top-p-sampling/)
- [Self-Consistency](https://protologue.com/t/self-consistency/)
- [Text Degeneration](https://protologue.com/t/text-degeneration/)

## Sources

- Holtzman et al. (2019). The Curious Case of Neural Text Degeneration. https://arxiv.org/abs/1904.09751

## Cite this entry

Protologue. (2026). Greedy Decoding. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0109). https://protologue.com/t/greedy-decoding/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)