conftrace
_
Papers
Trends
Conferences
Explore
More
Authors
Topics
Keywords
Papers
Trends
Conferences
Explore
Authors
Topics
Keywords
Achievements
← Authors
Copy link
Baosheng Wang
2 papers · 2026–2026 · 1 conference
· across top CS/AI conferences
Conferences
ACL (2)
Top co-authors
Kai Chen (1)
Xiaofeng Wang (1)
Xiaopeng Li (1)
Tian Xia (1)
Shasha Li (1)
Xiaofang Cai (1)
Jie Yu (1)
Songlei Jian (1)
Xi Wang (1)
Qianhong Guo (1)
Keywords
machine unlearning
(1)
safety alignment
(1)
model ranking
(1)
jailbreak attack
(1)
adversarial sample
(1)
large language model
(1)
benchmark-free evaluation
(1)
path rectification
(1)
mutual evaluation
(1)
Papers
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
ACL 2026
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
ACL 2026