Xiaocheng Li

Online-Optimized RAG for Tool Use and Function Calling

Risk Profiling and Modulation for LLMs

Reward Modeling with Ordinal Feedback: Wisdom of the Crowd

Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making

Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification

Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach