AI.info

Zhongxiang Dai

Explore Zhongxiang Dai on AI.info.

• CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
• Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts
• UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
• EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpus