BEIR

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  new activity about 2 months ago

BeIR/msmarco:Qrel file missing

nthakur  authored a paper about 2 months ago

FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents

nthakur  authored a paper about 2 months ago

Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses

View all activity

Team members 2