Meta's Toolformer Uses APIs to Outperform GPT-3 on Zero-Shot NLP Tasks

Meta AI Research announced Toolformer, a language model that learns to call APIs to help solve natural language processing (NLP) tasks. Toolformer automatically annotates a training dataset which is used to fine-tune the model and can outperform the much larger GPT-3 model on several zero-shot NLP tasks.

ai ai research apis call dataset deep learning gpt gpt-3 language language model language processing large language models meta meta ai meta ai research ml & data engineering natural natural language natural language processing nlp processing research training