Language Models are Few-Shot Learners

Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell · 2020

OpenAI

GPT-3. Scaling a decoder-only Transformer to 175B parameters and demonstrating in-context few-shot learning. The paper that crystallized the modern LLM paradigm.