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  authored a paper 4 days ago

Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval

nthakur  authored a paper 4 days ago

ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget

nthakur  authored a paper 8 months ago

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

View all activity

Team members 2