arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Yuanbo Xie"" — arXiv2 Search
Showing 1–3 of 3 results
/ Date
/ Name
Sep 18, 2025
Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
Apr 12, 2026
Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game
Mar 10, 2020
Observational detection of correlation between galaxy spins and initial conditions