ModelRefs / Greedy Decoding — AI Glossary
Greedy Decoding — AI Glossary
Decoding by always selecting the single highest-probability next token, producing deterministic but often repetitive output. Also called argmax decoding.
Overview
Greedy decoding is the fastest strategy—no branching, no sampling. Output is deterministic given the same prompt. It suffers from degenerate repetition and missing globally optimal completions. Useful for structured extraction, code generation with exact format requirements, and debugging (reproducibility).
Reference details
| Topic | inference |
|---|---|
| Also known as | argmax decoding |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Greedy Decoding — AI Glossary.
Frequently asked questions
What is Greedy Decoding?
Decoding by always selecting the single highest-probability next token, producing deterministic but often repetitive output.
Is Greedy Decoding the same as argmax decoding?
Yes — argmax decoding are common aliases for Greedy Decoding.
What concepts are related to Greedy Decoding?
Closely related concepts include beam search, sampling, temperature.