Get started
Author

Shiyao Cui

Observed names: Cui, Shiyao, Shi-Yao Cui
Institution: Tsinghua University
ORCID: 0000-0001-6738-6188
Observed ORCID: 0000-0001-6738-6188
OpenAlex ID: A5065782780
Agent-SafetyBench: Evaluating the Safety of LLM Agents
2024 · Zhang, Zhexin, Cui, Shiyao, et al. · arXiv (Cornell University) · 6
PDF
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
2025 · Junxiao Yang, Zhexin Zhang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 4
PDF
Label-Aware Chinese Event Detection with Heterogeneous Graph Attention Network
2024 · Shi-Yao Cui, Bo-Wen Yu, et al. · Journal of Computer Science and Technology · 4
LongSafety: Evaluating Long-Context Safety of Large Language Models
2025 · Yida Lu, Jiale Cheng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 3
PDF
From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
2024 · Zhang, Zhexin, Yang, Junxiao, et al. · arXiv (Cornell University) · 2
PDF
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
2025 · Cui, Shiyao, Feng, Xijia, et al. · arXiv (Cornell University) · 1
PDF
ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
2025 · Cui, Shiyao, Zhang, Qinglin, et al. · arXiv (Cornell University) · 1
PDF
LongSafety: Evaluating Long-Context Safety of Large Language Models
2025 · Lu, Yida, Cheng, Jiale, et al. · arXiv (Cornell University) · 1
PDF
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
2026 · Association for Computational Linguistics 2026, Cui, Shiyao, et al. · Underline Science Inc.
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
2026 · Zhexin Zhang, Xian Qi Loye, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
2025 · Zhang, Zhexin, Sun, Yuhao, et al. · arXiv (Cornell University)
PDF
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
2025 · Yang, Junxiao, Tu, Jinzhe, et al. · arXiv (Cornell University)
PDF
AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
2025 · Zhang, Zhexin, Lei, Leqi, et al. · arXiv (Cornell University)
PDF
Global Challenge for Safe and Secure LLMs Track 1
2024 · Jia, Xiaojun, Huang, Yihao, et al. · arXiv (Cornell University)
PDF
Works count: 14
Citation count: 22
H-index: 3
I10-index:
Year
Topic
Type