Dataset Groups Activity Stream MGSM The MGSM dataset is a multilingual math reasoning dataset containing around 7,500 training samples and 1,319 testing samples. BibTex: @dataset{Rohan_Anil_and_Andrew_M_Dai_and_Orhan_Firat_and_Melvin_Johnson_and_Dmitry_Lepikhin_and_Alexandre_Passos_and_Siamak_Shakeri_and_Emanuel_Taropa_2025, abstract = {The MGSM dataset is a multilingual math reasoning dataset containing around 7,500 training samples and 1,319 testing samples.}, author = {Rohan Anil and Andrew M. Dai and Orhan Firat and Melvin Johnson and Dmitry Lepikhin and Alexandre Passos and Siamak Shakeri and Emanuel Taropa}, doi = {10.57702/f17ipaia}, institution = {No Organization}, keyword = {'math reasoning', 'multilingual'}, month = {jan}, publisher = {TIB}, title = {MGSM}, url = {https://service.tib.eu/ldmservice/dataset/mgsm}, year = {2025} }
