Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models.
Avi SinghJohn D. Co-ReyesRishabh AgarwalAnkesh AnandPiyush PatilXavier GarciaPeter J. LiuJames HarrisonJaehoon LeeKelvin XuAaron ParisiAbhishek KumarAlex AlemiAlex RizkowskyAzade NovaBen AdlamBernd BohnetGamaleldin F. ElsayedHanie SedghiIgor MordatchIsabelle SimpsonIzzeddin GurJasper SnoekJeffrey PenningtonJiri HronKathleen KenealyKevin SwerskyKshiteej MahajanLaura CulpLechao XiaoMaxwell L. BileschiNoah ConstantRoman NovakRosanne LiuTris WarkentinYundi QianYamini BansalEthan DyerBehnam NeyshaburJascha Sohl-DicksteinNoah FiedelPublished in: CoRR (2023)