persian-eval

PersianMMLU Dataset Usage Agreement

By accessing and using the PersianMMLU dataset, you agree to comply with the terms outlined below. Please review them carefully:

License

The PersianMMLU dataset is distributed under the terms of the Creative Commons No Derivatives (CC ND) license. This license prohibits the creation of derivative works, including the development of benchmarking datasets derived from PersianMMLU.

Usage Guidelines

The dataset is intended solely for non-commercial, academic research purposes. This restriction is in place to avoid any conflicts with the educational activities conducted by Kanoon Farhangi Amoozesh (Cultural Educational Center). Researchers are obligated to adhere to these conditions. The utilization of the dataset should be confined to academic research and must respect the restrictions imposed by the CC ND license.

Reference

If you use the PersianMMLU dataset in your research work, please cite the following paper:

Title: "Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?"

Authors: Omid Ghahroodi, Marzia Nouri, Mohammad Vali Sanian, Alireza Sahebi, Doratossadat Dastgheib, Ehsaneddin Asgari, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban

Publication: arXiv preprint arXiv:2404.06644 (2024)

Joint Last/Corresponding Authorship: Ehsaneddin Asgari, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban

Joint Second Authorship : Marzia Nouri, Mohammad Vali Sanian, Alireza Sahebi

Additional Resources:

arxiv : https://arxiv.org/abs/2404.06644

Hugging face : https://huggingface.co/raia-center