Yue Xing

Assistant Professor, Michigan State University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

2 papers

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

LLM Safety Alignment is Divergence Estimation in Disguise

#4208 · Rajdeep Haldar, Ziyi Wang, Guang Lin, Yue Xing, Qifan Song

Unified theory LLM Alignment framework as divergence estimation between aligned and unaligned distributions; introduce KLDO, an alignment method, and advocate for compliance-refusal datasets to improve safety.

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

#1402 · Jie Ren, Zhenwei DAI, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C. Aggarwal, Hui Liu