conftrace_

Zhaoye Li

2 papers · 2025–2026 · 2 conferences · across top CS/AI conferences

Conferences

ACL (1) UAI (1)

Top co-authors

Ruochun Jin (1) Xiaopeng Li (1) Shasha Li (1) Wenjing Yang (1) Jing Ren (1) Huan Chen (1) Jie Yu (1) Siyuan Shen (1) Songlei Jian (1) Xi Wang (1)

Keywords

machine unlearning (1) safety alignment (1) jailbreak attack (1) adversarial sample (1) path rectification (1)

Papers

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification ACL 2026 Enhancing Uncertainty Quantification in Large Language Models through Semantic Graph Density UAI 2025