Tastle: Distract Large Language Models for Automatic Jailbreak Attack.
Zeguan XiaoYan YangGuanhua ChenYun ChenPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- context sensitive
- document retrieval
- retrieval model
- speech recognition
- test collection
- query expansion
- language modelling
- information retrieval
- statistical language models
- query terms
- language models for information retrieval
- smoothing methods
- ad hoc information retrieval
- language model for information retrieval
- relevance model
- pseudo relevance feedback
- term dependencies
- passage retrieval
- vector space model
- retrieval effectiveness