Actively learn from LLMs with uncertainty propagation for generalized category discovery

• Main Authors: LIANG, Jinggui, LIAO, Lizi, FEI, Hao, LI, Bobo, JIANG, Jing
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Large language models; LLMs; Category discovery; Natural language processing; Uncertainty propagation; Artificial Intelligence and Robotics; Computer Sciences
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/9700; https://ink.library.smu.edu.sg/context/sis_research/article/10700/viewcontent/2024.naacl_long.434.pdf

Generalized category discovery faces a key issue: the lack of supervision for new and unseen data categories. Traditional methods typically combine supervised pretraining with self-supervised learning to create models, and then employ clustering for category identification. However, these approaches...