Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield.
Jinhwa KimAli DerakhshanIan G. HarrisPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- document retrieval
- information retrieval
- label noise
- probabilistic model
- retrieval model
- statistical language models
- language modelling
- query expansion
- test collection
- smoothing methods
- query terms
- language models for information retrieval
- language model for information retrieval
- translation model
- context sensitive
- error rate
- training data
- decision trees
- vector space model
- pseudo relevance feedback
- term dependencies
- class labels
- information retrieval systems
- co occurrence
- ad hoc information retrieval