k.Frontier
FrontierOpenAI Blog
KeyRank 72Improving language understanding with unsupervised learning
This is a foundational result demonstrating that combining transformers with unsupervised pre-training achieves state-of-the-art performance across diverse language tasks—a methodology that would become the blueprint for modern LLMs like GPT-2, GPT-3, and beyond.
Why it ranks · · State-of-the-art results on diverse language task suite · June 2018
Read full story