🧑🔬 Xiangyu Qi — papers of 2024 — 3 papers, the most cited first3 papers · all years of Xiangyu QiSafety Alignment Should Be Made More Than Just a Few Tokens DeeparXiv:2406.05946Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, et al.2024 · 97 citationsSORRY-Bench: Systematically Evaluating Large Language Model Safety RefusalarXiv:2406.14598Tinghao Xie, Xiangyu Qi, Yi Zeng, et al.2024 · 87 citationsAssessing the Brittleness of Safety Alignment via Pruning and Low-Rank ModificationsarXiv:2402.05162Boyi Wei, Kaixuan Huang, Yangsibo Huang, et al.2024 · 66 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/xiangyu-qi/year/2024/