Lean Wang

Gradient Knowledge Distillation for Pre-trained Language Models

Xu Sun, Lei Li, Lean Wang, 2022, ArXiv.

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Hao Zhou, Lei Li, Hao Zhou, 2023, EMNLP.

Towards Codable Text Watermarking for Large Language Models

Jie Zhou, Fandong Meng, Yankai Lin, 2023, ArXiv.