AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.
Xiaogeng LiuNan XuMuhao ChenChaowei XiaoPublished in: ICLR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- information retrieval
- language modelling
- retrieval model
- test collection
- context sensitive
- query expansion
- statistical language models
- smoothing methods
- query terms
- ad hoc information retrieval
- language model for information retrieval
- relevance model
- pseudo feedback
- okapi bm
- language models for information retrieval
- vector space model
- translation model
- retrieval effectiveness
- cross lingual
- document ranking
- text classification
- query processing
- word error rate
- image retrieval
- decision trees
- feature selection