Home › Research Papers › Language Models are Few-Shot Learners (2020)
Language Models are Few-Shot Learners (2020)
Research Paper
Scaling
The GPT-3 paper: capability from scale, tasks from prompts.
You're looking at a research-paper record: a landmark paper and what it introduced to the field.
OpenAI showed that a 175B-parameter model could perform translation, arithmetic and reasoning tasks from examples in its prompt alone — in-context learning — validating the bet that scale itself produces generality and launching the API era.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Introduced in
Sources
Record reviewed as of 2026-01-15 — see Methodology.