AI & ML interests

BEIR (Benchmarking IR) consists of a homogenous benchmark for diverse sentence or passage level IR tasks. It provides a common and easy framework for the cross-domain evaluation of your retrieval models.

Recent Activity

nthakur  updated a dataset 4 days ago
BeIR/cqadupstack
nthakur  published a dataset 4 days ago
BeIR/cqadupstack
View all activity

nthakur 
in BeIR/fever 4 days ago
nthakur 
in BeIR/fiqa 4 days ago