LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Paper • 2604.12710 • Published • 5
HaoranLiu
HaoranLiu
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety upvoted a paper 12 months ago
How Should We Enhance the Safety of Large Reasoning Models: An Empirical
StudyOrganizations
None yet
upvoted a paper about 1 month ago
upvoted 3
papers 12 months ago
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!
Paper • 2505.15656 • Published • 15
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
Paper • 2505.15404 • Published • 13
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Paper • 2505.13529 • Published • 11