Microsoft researcher points out BERT was already called an LLM back in 2019

JFPuget · x · 2026-09-20

Microsoft researcher JFPuget reminds people that "LLM" isn't a new term — BERT and other large pretrained language models were already being called LLMs in 2019. He cites Lilian Weng's January 2019 blog post Generalized Language Models, which surveys the lineage from CoVe, ELMo and ULMFiT through GPT, BERT, GPT-2, and later T5, GPT-3, XLNet, BART and ELECTRA.

Original post →

More from Research

Research channel →