BEIR

The BEIR dataset is a large-scale zero-shot evaluation dataset for information retrieval models, consisting of 13,000 documents and 1,000 questions.

Data and Resources

Cite this as

Jurek Leonhardt, Henrik Müller, Koustav Rudra, Megha Khosla, Abhijit Anand, Avishek Anand (2024). Dataset: BEIR. https://doi.org/10.57702/l85eg5e4

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2404.13950
Citation
  • https://doi.org/10.48550/arXiv.2211.08769
  • https://doi.org/10.48550/arXiv.2310.05380
  • https://doi.org/10.48550/arXiv.2311.01263
Author Jurek Leonhardt
More Authors
Henrik Müller
Koustav Rudra
Megha Khosla
Abhijit Anand
Avishek Anand
Homepage https://huggingface.co/datasets/beir