8 papers
What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
Qin Yang, Lu Malloy, Joshua Lee +4
Large language model (LLM)-powered content moderation systems are a critical defense against harmful online content. However, they operate primarily on tokenized text and often ove…
Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
Amin Banayeeanzade, Qingchuan Yang, Dhruv Tarsadiya +6
Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible ou…
Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
Meisam Mohammady, Qin Yang, Nicholas Stout +4
Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tun…
U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation
Zezheng Wu, Rui Wang, Xinghe Cheng +4
Generative Recommendation (GenRec) typically leverages Large Language Models (LLMs) to redefine personalization as an instruction-driven sequence generation task. However, fine-tun…
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
Amin Banayeeanzade, Qingchuan Yang, Deqing Fu +6
High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for do…
LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena
Qingchuan Yang, Simon Mahns, Sida Li +3
Forecasting is not only a fundamental intellectual pursuit but also is of significant importance to societal systems such as finance and economics. With the rapid advances of large…
PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
Qin Yang, Nicholas Stout, Meisam Mohammady +6
Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient…
LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
Qin Yang, Meisam Mohammad, Han Wang +5
Differentially Private Stochastic Gradient Descent (DP-SGD) and its variants have been proposed to ensure rigorous privacy for fine-tuning large-scale pre-trained language models.…