Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Tingyu Li

Tingyu Li

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1

Frequent co-authors

Yu Cui1×
Ruiqing Yue1×
Sicheng Pan1×
Zhuoyu Sun1×
Xufeng Zhang1×
Baohan Huang1×

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 →