Publications

CCS 2026 (CORE A* / CCF A)SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment

Qingyu Meng, Yiwei Zha, Jiahuan Pei, Koen Hindriks, Herbert Bos, Min Chen

To appear in ACM CCS 2026[PDF] [arXiv] [Website]

A training-time parameter-efficient defense that reinforces shared experts in hybrid MoE architectures for router-independent safety alignment.
ACL 2026 (CORE A* / CCF A)StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation

Qingyu Meng, Min Chen, Dingming Liu, Yifan Mo, Yue Su, Xin Sun, Koen Hindriks, Jiahuan Pei

In Findings of ACL 2026[PDF] [BibTeX]

A multi-LLM agent framework for controllable motivational interviewing dialogue generation grounded in situational stories derived from questionnaires.
ACL 2026 (CORE A* / CCF A)SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity

Yifan Mo, Xiao Fu, Yue Su, Qingyu Meng, Koen Hindriks, Qingzhi Liu, Jiahuan Pei

In Findings of ACL 2026[PDF] [BibTeX]

A comprehensive workflow and evaluation protocol for assessing LLMs' ability to generate mathematical equations from scientific texts.
INLG 2026 (CORE B)Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers

Xin Sun, Yue Su, Yifan Mo, Qingyu Meng, Yuxuan Li, Min Chen, Mengyuan Zhang, Saku Sugawara, Charlotte Gerritsen, Sander L. Koole, Koen Hindriks, Jiahuan Pei

To appear in INLG 2026[PDF] [BibTeX]

A three-layer trust framework for language-based mental health AI systems that distinguishes human-oriented trust, interaction-oriented trustworthiness, and AI-oriented trustworthiness.