Wenhua Wang

Stepwise-Querying: Distilling Reasoning without Access to Teacher Chain-of-Thought

This work proposes Stepwise Querying, which elicits step-specific explanations without requiring access to the teacher's internal chain-of-thought (CoT) traces, and introduces Stepwise Explanation Information Gain (SEIG), a diagnostic based on the log-ratio of a frozen student's probabilities of correct step completion...

PI-SAFE: Practical Privacy-Preserving LLM Inference With Adversarial Fine-Tuning for Optimized Utility

Cloud-based Large Language Model (LLM) inference services typically require users to submit plain-text inputs, thereby posing severe privacy risks. Existing privacy-preserving paradigms are mostly task-specific and often necessitate pervasive modifications to the entire server-side model. This reliance introduces subst...

Diffusion-Guided Multi-Objective Reinforcement Learning for Hybrid Action Optimization in Collaborative Edge AIGC Networks