1 citations · 2 across the 10 of their papers we have counts for
Showing 2026 · cs.CRShow all
2 papers · 2 filters
cs.CR2026
Differential Privacy Protected Preference Alignment on Survey Derived Data
Xiuyuan Qi, Yi Wang, Wenjie Wang
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when derived from surveys about poli…
cs.CR2026
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models
Yi Wang, Xiuyuan Qi, Dongqi Han +2
Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated use of shared parameters across recurrent steps. Since each r…