EW-Tune: A Framework for Privately Fine-Tuning Large Language Models with Differential Privacy.
Rouzbeh BehniaMohammadReza EbrahimiJason PachecoBalaji PadmanabhanPublished in: ICDM (Workshops) (2022)
Keyphrases
- language model
- differential privacy
- fine tuning
- probabilistic model
- differentially private
- privacy preserving data mining algorithms
- n gram
- language modeling
- privacy guarantees
- statistical language models
- retrieval model
- information retrieval
- query terms
- test collection
- document retrieval
- private data
- web search
- language modelling
- user behavior
- relevance model
- privacy preserving
- knowledge discovery
- query processing
- bayesian networks