We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large- scale pre-trained language models, which achieve the state-of-the-art privacy versus utility …
The proliferation of Large Language Models (LLMs) has driven considerable interest in fine- tuning them with domain-specific data to create specialized language models. Nevertheless …
Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back- propagation, safeguarding training data from privacy leakage, particularly membership …
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre …
Y Li, Z Tan, Y Liu - arXiv preprint arXiv:2305.06212, 2023 - arxiv.org
Prompt tuning provides an efficient way for users to customize Large Language Models (LLMs) with their private data in the emerging LLM service scenario. However, the sensitive …
We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work …
Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the …
Privacy preservation remains a key challenge in data mining and Natural Language Understanding (NLU). Previous research shows that the input text or even text embeddings …
The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private …