conftrace
_
Papers
Trends
Conferences
Explore
More
Authors
Topics
Keywords
Papers
Trends
Conferences
Explore
Authors
Topics
Keywords
Achievements
← Authors
Copy link
Yuexiao Liu
1 papers · 2026–2026 · 1 conference
· across top CS/AI conferences
Conferences
ACL (1)
Top co-authors
Lijun Li (1)
Jing Shao (1)
Xingjun Wang (1)
Keywords
safety alignment
(1)
harmful fine-tuning
(1)
attack success rate
(1)
reinforcement learning with verifiable reward
(1)
alignment reversibility
(1)
Papers
HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment
ACL 2026