LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models.
Qin YangMeisam MohammadyHan WangAli PayaniAshish KunduKai ShuYan YanYuan HongPublished in: CoRR (2024)
Keyphrases
- language model
- fine tuning
- differentially private
- language modeling
- differential privacy
- n gram
- privacy preserving
- speech recognition
- information retrieval
- document retrieval
- probabilistic model
- query expansion
- query terms
- privacy guarantees
- language modelling
- statistical language models
- retrieval model
- test collection
- language models for information retrieval
- smoothing methods
- fine tuned
- document ranking
- translation model
- contingency tables
- relevance model
- learning to rank