Yueqi Xie 谢悦琪

👋 Hi!

I am Yueqi Xie, a postdoctoral research associate at Princeton University, working with Prof. Yu Xie on AI and society. I received my Ph.D. in computer science from HKUST, advised by Prof. Qifeng Chen and Prof. Sunghun KIM. Before HKUST, I received my B.S. with honors from Peking University EECS.

Email  /  Google Scholar

I'm happy to discuss and collaborate on related research, and I warmly encourage undergraduate and early graduate students to reach out with any questions or topics about research and academic life. I especially encourage students from underrepresented groups to get in touch.

 profile photo
Research

I work on societal intelligence, focusing on socially responsible AI, social intelligence, and human–AI interaction. We aim to enable AI to better understand human and society, collaborate with humans, and integrate safely and reliably into society.

Topics I currently focus on:

  • Socially Responsible AI: AI safety, privacy protection, and governance mechanisms.
  • Social Intelligence: Social understanding, social reasoning, and social simulation.
  • Human–AI Interaction: Human–AI collaboration and the impact of AI on individuals, groups, and society.
Selected Work

(* joint first authors, # corresponding authors)

Full Publication List on Google Scholar.
Defending ChatGPT against Jailbreak Attack via Self-Reminder
Yueqi Xie*, Jingwei Yi*, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, Fangzhao Wu
Nature Machine Intelligence, 2023
/ / / Media Coverage: TechXplore, Tech Times
GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
Yueqi Xie, Minghong Fang, Renjie Pi, Neil Gong
Annual Meeting of the Association for Computational Linguistics (ACL), 2024
/ /
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi*, Yueqi Xie*, Bin Zhu, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
/ /
Auditing Unauthorized Training Data from AI Generated Content using Information Isotopes
Tao Qi, Jinhua Yin, Dongqi Cai, Yueqi Xie#, Huili Wang, Zhiyang Hu, Peiru Yang, Guoshun Nan, Zhili Zhou, Lingjuan Lyu, Shangguang Wang#, Yongfeng Huang#, Nicholas D. Lane#
Nature Communications, 2026
Learning behavior accounts for background-related advantage in AI-assisted education
Jingwei Yi, Yueqi Xie, Jiyan He, Rui Ye, Junming Huang, Bin Zhu, Sean Rintel, Yu Xie, Xing Xie, Fangzhao Wu
arXiv preprint, 2026
Measuring Human Contribution in AI-Assisted Content Generation
Yueqi Xie*, Tao Qi*, Jingwei Yi*, Ryan Whalen, Junming Huang, Qian Ding, Yu Xie, Xing Xie, Fangzhao Wu
Annual Meeting of the Association for Computational Linguistics (ACL), 2026
/ /
Uncovering inequalities in new knowledge learning by large language models across different languages
Chenglong Wang, Haoyu Tang, Xiyuan Yang, Yueqi Xie#, Jina Suh, Sunayana Sitaram, Junming Huang, Yu Xie, Pengjun Zhao#, Zhaoya Gong#, Xing Xie, Fangzhao Wu#
Proc. Natl. Acad. Sci. U.S.A. (PNAS), 2025
Evaluating the statistical realism of LLM-generated social science data
Yueqi Xie, Lemeng Liang, Shuzhen Li, Yifu Lu, Zhiwen Xiao, Mengdi Shi, Junming Huang, Mengdi Wang, and Yu Xie
Proc. Natl. Acad. Sci. U.S.A. (PNAS), 2026
Honors and Awards
  • Young Scientists Program Scholarship, (2 in CSE Department), HKUST, 2025
  • WSDM Best Paper Award Honorable Mention, 2023
  • Research Travel Grant, HKUST, 2022, 2023
  • Outstanding Graduate in Peking University, 2020
  • Peking University Scholarship, 2018, 2019
  • EmotioNet Challenge 2nd Prize, 2018

Source code from Jon Barron, Aljaž Božič, XINTAO and Ekun.