no code implementations • 17 Feb 2024 • Xuan Ren, Biao Wu, Lingqiao Liu
The potential for overfitting on a limited number of examples can negatively impact the model's ability to generalize and retain its original skills.
no code implementations • 28 Jun 2023 • Xuan Ren, Lingqiao Liu
In this paper, we propose a novel approach that goes beyond traditional one-shot generation methods by introducing a multi-step process consisting of generation, verification, and correction stages.
no code implementations • 23 May 2023 • Linyi Yang, Yaoxiao Song, Xuan Ren, Chenyang Lyu, Yidong Wang, Lingqiao Liu, Jindong Wang, Jennifer Foster, Yue Zhang
Machine learning (ML) systems in natural language processing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differs from the training data distribution.