PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages Paper • 2504.04377 • Published Apr 6
SciDr at SDU-2020: IDEAS -- Identifying and Disambiguating Everyday Acronyms for Scientific Domain Paper • 2102.08818 • Published Feb 17, 2021
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents Paper • 2410.13886 • Published Oct 11, 2024
PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models Paper • 2405.09373 • Published May 15, 2024 • 1