GEMv2: Multilingual NLG Benchmarking in a Single Line of Code.
Sebastian GehrmannAbhik BhattacharjeeAbinaya MahendiranAlex WangAlexandros PapangelisAman MadaanAngelina McMillan-MajorAnna ShvetsAshish UpadhyayBingsheng YaoBryan WilieChandra BhagavatulaChaobin YouCraig ThomsonCristina GarbaceaDakuo WangDaniel DeutschDeyi XiongDi JinDimitra GkatziaDragomir R. RadevElizabeth ClarkEsin DurmusFaisal LadhakFilip GinterGenta Indra WinataHendrik StrobeltHiroaki HayashiJekaterina NovikovaJenna KanervaJenny ChimJiawei ZhouJordan CliveJoshua MaynezJoão SedocJuraj JuraskaKaustubh D. DholeKhyathi Raghavi ChanduLaura Perez-BeltrachiniLeonardo F. R. RibeiroLewis TunstallLi ZhangMahima PushkarnaMathias CreutzMichael WhiteMihir Sanjay KaleMoussa Kamal EddineNico DaheimNishant SubramaniOndrej DusekPaul Pu LiangPawan Sasanka AmmanamanchiQi ZhuRatish PuduppullyReno KrizRifat ShahriyarRonald CardenasSaad MahamoodSalomey OseiSamuel CahyawijayaSanja StajnerSébastien MontellaShailza JollySimon MilleTahmid HasanTianhao ShenTosin P. AMahidewumiVikas RaunakVipul RahejaVitaly NikolaevVivian TsaiYacine JerniteYing XuYisi SangYixin LiuYufang HouPublished in: CoRR (2022)