Tingyu Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1
Frequent co-authors
Research Timeline
2026
Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization
This paper explores safety risks in humorization of large language models (LLMs) and introduces HumorSafe framework for evaluating latent safety risks.
Highlighted terms show continued research focus across papers
Papers
cs.CREmpiricalRecentJul 17, 2026
Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization
Yu Cui, Ruiqing Yue, Tingyu Li, Sicheng Pan +5 more
This paper explores safety risks in humorization of large language models (LLMs) and introduces HumorSafe framework for evaluating latent safety risks.
View →