1 code implementation • 10 Apr 2024 • Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
In this paper, we explore the hypothesis that LLMs process concepts of varying complexities in different layers, introducing the idea of "Concept Depth" to suggest that more complex concepts are typically acquired in deeper layers.
no code implementations • 19 Oct 2023 • Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu, Michael R. Lyu
This paper identifies a cultural dominance issue within large language models (LLMs) due to the predominant use of English data in model training (e. g., ChatGPT).
no code implementations • 18 Aug 2023 • Wenxuan Wang, Jingyuan Huang, Jen-tse Huang, Chang Chen, Jiazhen Gu, Pinjia He, Michael R. Lyu
Moreover, through retraining the models with the test cases generated by OASIS, the robustness of the moderation model can be improved without performance degradation.
no code implementations • 23 May 2023 • Wenxuan Wang, Jingyuan Huang, Chang Chen, Jiazhen Gu, Jianping Zhang, Weibin Wu, Pinjia He, Michael Lyu
To this end, content moderation software has been widely deployed on these platforms to detect and blocks toxic content.