SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference.
Abhijit MishraMingda LiSoham DeoPublished in: CoRR (2023)
Keyphrases
- fine tuning
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- fine tuned
- viable alternative
- document retrieval
- retrieval model
- encryption key
- speech recognition
- context sensitive
- statistical language models
- query expansion
- test collection
- language modelling
- smoothing methods
- language models for information retrieval
- bayesian networks
- passage retrieval
- document ranking
- pseudo relevance feedback
- vector space model
- encryption scheme
- relevance model
- word error rate
- cross lingual
- retrieval effectiveness
- ad hoc information retrieval
- information retrieval systems