Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Private Direct Preference Optimization for LLM Alignment
Yangfan Jiang, Fei Wei, Ergute Bao +3
Direct preference optimization (DPO) is now a standard method for aligning large language models (LLMs) using human preference data. Each DPO example contains a prompt and a pair o…
cs.CR2024
AAA: an Adaptive Mechanism for Locally Differential Private Mean Estimation
Fei Wei, Ergute Bao, Xiaokui Xiao +2
Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data local…