4 papers
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…
Accurate Table Question Answering with Accessible LLMs
Yangfan Jiang, Fei Wei, Ergute Bao +4
Given a table T in a database and a question Q in natural language, the table question answering (TQA) task aims to return an accurate answer to Q based on the content of T. Recent…
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…
Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
Xinjian Luo, Yangfan Jiang, Fei Wei +3
Diffusion models have recently gained significant attention in both academia and industry due to their impressive generative performance in terms of both sampling quality and distr…