SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.
Alexander RobeyEric WongHamed HassaniGeorge J. PappasPublished in: CoRR (2023)
Keyphrases
- language model
- ddos attacks
- language modeling
- probabilistic model
- n gram
- speech recognition
- document retrieval
- information retrieval
- query expansion
- language modelling
- statistical language models
- test collection
- context sensitive
- retrieval model
- language models for information retrieval
- ad hoc information retrieval
- query terms
- vector space model
- smoothing methods
- word error rate
- language model for information retrieval
- okapi bm
- pseudo feedback
- document length
- query specific
- translation model