1 citations · 2 across the 8 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.CL2024
Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs
Zhuo Li, Yuhao Du, Jinpeng Hu +2
Large language models (LLMs) have shown success in generating high-quality responses. In order to achieve better alignment with LLMs with human preference, various works are propos…
cs.CL2024★ 1 cited
Atoxia: Red-teaming Large Language Models with Target Toxic Answers
Yuhao Du, Zhuo Li, Pengyu Cheng +2
Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, o…
cs.LG2024★ 1 cited
Extracting Clean and Balanced Subset for Noisy Long-tailed Classification
Zhuo Li, He Zhao, Zhen Li +3
Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim…