SentinelLMs: Encrypted Input Adaptation and Fine-Tuning of Language Models for Private and Secure Inference.
Abhijit MishraMingda LiSoham DeoPublished in: AAAI (2024)
Keyphrases
- fine tuning
- language model
- language modeling
- fine tuned
- n gram
- document retrieval
- information retrieval
- viable alternative
- statistical language models
- encryption key
- probabilistic model
- language modelling
- test collection
- query expansion
- speech recognition
- retrieval model
- smoothing methods
- query terms
- privacy preserving
- vector space model
- context sensitive
- ad hoc information retrieval
- language model for information retrieval
- okapi bm
- bayesian networks
- document ranking
- encryption scheme
- relevance model
- retrieval effectiveness
- term dependencies
- query specific
- translation model
- pseudo relevance feedback
- text retrieval