---
title: "Language Models are Few-Shot Learners"
description: "GPT-3 asks whether one pretrained language model can take on a new task from text alone, without changing its weights. Read it to see how an instruction and zero, one, or several worked examples turn the prompt into a temporary task specification, why larger models used that context more effectively on many benchmarks, and where the result remained uneven or contaminated."
canonical_url: "https://fanout.sh/daily/2026-09-03-gpt3-few-shot-learners"
md_url: "https://fanout.sh/daily/2026-09-03-gpt3-few-shot-learners.md"
last_updated: "2026-09-03"
access: "public"
---

# Language Models are Few-Shot Learners

GPT-3 asks whether one pretrained language model can take on a new task from text alone, without changing its weights. Read it to see how an instruction and zero, one, or several worked examples turn the prompt into a temporary task specification, why larger models used that context more effectively on many benchmarks, and where the result remained uneven or contaminated.

## Paper details

- Authors: Brown et al.

- Venue: NeurIPS 2020

- Track: AI Research

- Difficulty: Easy

- Reading time: 35 min

- Original paper: https://arxiv.org/abs/2005.14165v4

## What you will learn

- How zero-shot, one-shot, and few-shot prompting change the examples inside the context while the pretrained model weights remain fixed.

- Why next-token prediction can continue a demonstrated input-output pattern, how a finite context limits the teaching set, and why more examples are not always better.

- How the paper's CoQA and SuperGLUE results coexist with chance-level WiC, benchmark-overlap concerns, high compute cost, bias, and uncertainty about task learning versus task recognition.

## Continue exploring

[Explore few-shot learning in Fanout](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Afew-shot-learning): Connect GPT-3's prompt-only task adaptation to Fanout's few-shot-learning node, autoregressive models, prompt engineering, chain-of-thought, and later in-context methods.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md