GEM benchmark

AI & ML interests

We develop infrastructure for the evaluation of generated text.

Recent Activity

j-chim  authored a paper 8 days ago

The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset

j-chim  authored a paper 8 days ago

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code

j-chim  authored a paper 8 days ago

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

View all activity

Team members 100