4 papers
SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
Qingyu Meng, Yiwei Zha, Jiahuan Pei +3
Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling massive parameter growth with…
SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity
Yifan Mo, Xiao Fu, Yue Su +4
This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts. Prior work faces challenges in unstructured grounding,…
StoryMI: Steerable Multi-Agent Therapeutic Dialogue Generation
Qingyu Meng, Min Chen, Dingming Liu +5
Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in m…
Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers
Xin Sun, Yue Su, Yifan Mo +9
Language-based AI is increasingly deployed for mental health support, yet trust is evaluated in interdisciplinary but operationally misaligned ways: NLP and AI work measures robust…