Chenxiao Yu is a first-year Ph.D. student in Computer Science at the University of Southern California, where he is advised by Prof. Yue Zhao. He also works closely with Prof. Morteza Dehghani. Chenxiao is from Hangzhou, China.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics · 2026
Shawn Li†, Chenxiao Yu†, Zhiyu Ni†, Hao Li, Charith Peris, Chaowei Xiao, Yue Zhao
Current defenses against prompt injection attacks rely on surface-level heuristics rather than robust understanding of attack patterns.
Proceedings of the 43rd International Conference on Machine Learning · 2026
Jiate Li, Defu Cao, Li Li, Wei Yang, Yuehan Qin, Chenxiao Yu, Tiannuo Yang, Ryan A. Rossi, Yan Liu, Xiyang Hu, Yue Zhao
A query-agnostic black-box attack framework that manipulates LLM-based retrieval systems without knowledge of user queries.
arXiv Preprint · 2026
Chenxiao Yu†, Bowen Yi†, Farzan Karimi-Malekabadi, Suhaib Abdurahman, Jinyi Ye, Shrikanth Narayanan, Yue Zhao, Morteza Dehghani
Do LLMs have human-like moral cognition?
Proceedings of the AAAI Conference on Artificial Intelligence · 2026
Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao, Ziyi Wang, Chenxiao Yu, Shawn Li, Jie Wang, Xiyang Hu, Yue Zhao
A causal intervention framework that reduces hallucinations in LLMs by identifying and adjusting unstable internal pathways.
arXiv Preprint · 2025
Suhaib Abdurahman, Farzan Karimi-Malekabadi, Chenxiao Yu, Nour S. Kteily, Morteza Dehghani
A causal analysis of how realistic threat perception drives intergroup conflict using generative-agent simulations.
Two papers accepted at ACL 2026 (Main + Findings)! 🎉
Received the USC Viterbi/Annenberg Fellowship! 🎓
Received the USC 2026 CCLS Seed Funding Award! 🏆
See U Guys @ NeurIPS 2025🎉
