29 citations · 93 across the 13 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.CL2023★ 1 cited
Unveiling the Implicit Toxicity in Large Language Models
Jiaxin Wen, Pei Ke, Hao Sun +4
The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent st…
cs.CL2023★ 16 cited
Safety Assessment of Chinese Large Language Models
Hao Sun, Zhexin Zhang, Jiawen Deng +2
With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting an…
cs.AI2023★ 12 cited
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements
Jiawen Deng, Jiale Cheng, Hao Sun +2
As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to un…