no code implementations • 1 Oct 2023 • Yachuan Liu, Liang Chen, Jindong Wang, Qiaozhu Mei, Xing Xie
We hope this initial work can shed light on future research of LLMs evaluation.
no code implementations • 9 May 2023 • Yachuan Liu, Bohan Zhang, Qiaozhu Mei, Paramveer Dhillon
Recent work has shown that standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on underrepresented groups due to the prevalence of spurious features.