Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization.
Zhexin ZhangJunxiao YangPei KeMinlie HuangPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- query expansion
- document retrieval
- information retrieval
- speech recognition
- statistical language models
- retrieval model
- test collection
- language modelling
- ddos attacks
- document ranking
- smoothing methods
- context sensitive
- vector space model
- term dependencies
- language models for information retrieval
- language model for information retrieval
- relevance model
- query terms
- word error rate
- pseudo relevance feedback
- translation model
- passage retrieval
- document length
- okapi bm
- ad hoc information retrieval
- statistical language modeling
- information extraction