4 papers
Differentially Private Retrieval-Augmented Generation
Tingting Tang, James Flemings, Yongqin Wang +1
Retrieval-augmented generation (RAG) is a widely used framework for reducing hallucinations in large language models (LLMs) on domain-specific tasks by retrieving relevant document…
Personalizing Agent Privacy Decisions via Logical Entailment
James Flemings, Ren Yi, Octavian Suciu +3
Personal large language model (LLM) agents increasingly perform tasks that require access to user data, raising concerns about appropriate data disclosure. We show that relying sol…
Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs
James Flemings, Haosheng Gan, Hongyi Li +2
In-context learning (ICL) has shown promising improvement in downstream task adaptation of LLMs by augmenting prompts with relevant input-output examples (demonstrations). However,…
Adaptively Private Next-Token Prediction of Large Language Models
James Flemings, Meisam Razaviyayn, Murali Annavaram
As Large Language Models (LLMs) proliferate, developing privacy safeguards for these models is crucial. One popular safeguard involves training LLMs in a differentially private man…