GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning Zhouxiang Fang, Jiawei Zhou, Hanjie Chen Preprint. [Arxiv]
ICL CIPHERS: Quantifying “Learning” in In-Context Learning via Substitution Ciphers Zhouxiang Fang, Aayush Mishra, Muhan Gao, Anqi Liu, Daniel Khashabi The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), Suzhou, China, Nov 2025. [Paper][Code][Slides][Video]
Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions
Hanjie Chen*, Zhouxiang Fang*, Yash Singla, Mark Dredze 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL), Albuquerque, New Mexico, United States, May 2025. [Paper][Code]
How to generate popular post headlines on social media? Zhouxiang Fang, Min Yu, Zhendong Fu, Boning Zhang, Xuanwen Huang, Xiaoqi Tang, Yang Yang AI Open, Jan. 2024. [Paper]