I am an Assistant Professor in Machine Learning Group, at the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen. From 2024 to 2025, I worked as a postdoctoral researcher in Machine Learning Department at MBZUAI, working with Prof.Fakhri Karray, where my research focused on enhancing the trustworthiness and interpretability of large language models (LLMs), particularly in the areas of hallucination detection, safety, and privacy. I completed my PhD at University of Stavanger supervised by Prof. Steinar Evje between 2021 and 2023, with research in AI for Mathematics, specifically on using AI methods to identify the partial differential equations (PDEs) underlying complex dynamical systems. I had both my bachelor’s and master’s degrees in Applied Mathematics. In addition to my academic experience, I also have more than two years of industry experience at Alibaba Group as a Senior Algorithm Engineer.

My research lies at the intersection of artificial intelligence and mathematics. We leverage mathematical theory to improve the trustworthiness and interpretability of AI models, with a particular focus on large language models, including hallucination detection, privacy, and safety. In addition, we explore the use of AI for scientific discovery, including identifying dynamical systems from observational data. Currently, my research group focuses on the following directions:

• LLM-based Agentic AI Systems: planning, reasoning, continual learning, and safety
• Trustworthy LLMs: hallucination detection, safety, and privacy
• AI for Mathematics and Scientific Computing

🎓 Available Positions

I am actively looking for highly motivated PhD students, CSC-funded students, Master students and Visiting students. If you are interested in working with me on generative models, LLM-based agentic system, scientific computing and related interdisciplinary topics, please feel free to contact me at qing.li@rug.nl. Here are some suggestions for preparing the email:

• Please use Subject Line as: “PhD/Master/CSC/Visiting Student + YourName”

• Please highlight your publications (if applicable), GPA/ranking, TOEFL and IELTS scores, and anything important

• Attach your CV

PhD Position Information

1. What can you expect from us?
   • €3059—€3881 per month
   • 232 vacation hours per year, based on a 38-hour workweek (1.0 FTE). You can also work more or fewer hours in exchange for more or fewer free hours. For example, with a 40-hour workweek, you save 96 extra free hours, and with a 36-hour workweek, you lose 96 hours.
   • End-of-year bonus of 8.3% and 8% holiday allowance.
   • Extensive opportunities for personal and professional development.
2. Application Link
   • PhD position Toward Trustworthy and Adaptive Agentic AI Systems
   • If the link is no longer available, please contact me directly at qing.li@rug.nl

🔥 News

• 2026.5 🎉1 paper is accepted by ICML 2026
• 2026.4 🎉1 paper is accepted by ACL 2026
• 2026.2 🎉1 paper is accepted by CVPR 2026
• 2025.7: 🎉1 paper is accepted by ICCV 2025
• 2025.5: 🎉 3 papers is accepted by ACL 2025 and 1 paper accepted by ACL findings 2025
• 2024.12: 🎉 One paper is accepted by AAAI 2025

📝 Recent Publications

• International Conference on Machine Learning (ICML 2026) Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs, Lecheng Yan, Ruizhe Li, Guanhua Chen, Qing Li, Jiahui Geng, Wenxi Li, Longyue Wang, Chenyang Lyu

• Annual Meeting of the Association for Computational Linguistics (ACL) 2026 CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval, Jiahui Geng, Fengyu Cai, Shaobo Cui, Qing Li, Liangwei Chen, Chenyang Lyu, Haonan Li, Derui Zhu, Alexander Pretschner, Heinz Koeppl, Fakhri Karray

• Conference on Computer Vision and Pattern Recognition (CVPR) 2026 CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval, Jiahui Geng, Qing Li, Fengyu Cai, Fakhri Karray

• International Conference on Computer Vision (ICCV) 2025 SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders, Jiahui Geng, Qing Li

• Annual Meeting of the Association for Computational Linguistics (ACL) 2025 HD-NDEs: Neural differential equations for hallucination detection in LLMs, Qing Li, Jiahui Geng, Zongxiong Chen, Derui Zhu, Yuxia Wang, Congbo Ma, Chenyang Lyu, Fakhri Karray

• Annual Meeting of the Association for Computational Linguistics (ACL) 2025 VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration, Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

• Annual Meeting of the Association for Computational Linguistics (ACL) 2025 Explicit and Implicit Data Augmentation for Social Event Detection, Congbo Ma, Yuxia Wang, Jia Wu, Jian Yang, Jing Du, Zitai Qiu, Qing Li, Hu Wang, Preslav Nakov

• Annual Meeting of the Association for Computational Linguistics (ACL) 2025 Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language, Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu, Xuanfan Ni, Tianqi Shi, Yu Zhao, Yefeng Liu, Chenyu Zhu, Ruizhe Li, Jiahui Geng, Qing Li, Yu Tong, Longyue Wang, Weihua Luo, Kaifu Zhang

• Association for the Advancement of Artificial Intelligence (AAAI) 2025 Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update, Qing Li, Jiahui Geng, Zongxiong Chen, Kun Song, Lei Ma, Fakhri Karray

💬 Invited Talks and Tutorials

• 2025.11, Building Trustworthy and Interpretable Generative AI Systems, New York University Abu Dhabi, United Arab Emirates

⭐ Services

• 2025, Area Chair, ACL, EMNLP; Program Committee, AAAI, ICCV, NeurIPS
• 2024, Program Committee, ICLR, AAAI, ACL, EMNLP