https://paperswithcode.com/sota/question-answering-on-truthfulqa
GPT-3: Language Models are Few-Shot Learners
Language Models are Unsupervised Multitask Learners
T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://arxiv.org/pdf/2109.07958#page=3
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
https://openai.com/index/gpt-4-research/