Open Sesame! Universal Black Box Jailbreaking of Large Language Models.
Raz LapidRon LangbergMoshe SipperPublished in: CoRR (2023)
Keyphrases
- black box
- language model
- language modeling
- document retrieval
- n gram
- query expansion
- speech recognition
- black boxes
- probabilistic model
- language modelling
- retrieval model
- test collection
- information retrieval
- white box
- statistical language models
- context sensitive
- integration testing
- test cases
- smoothing methods
- vector space model
- document ranking
- pseudo relevance feedback
- ad hoc information retrieval
- cross lingual
- white box testing
- query specific
- document length
- relevance model
- okapi bm