ObscurePrompt: Jailbreaking Large Language Models via Obscure Input.
Yue HuangJingyu TangDongping ChenBingda TangYao WanLichao SunXiangliang ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- information retrieval
- document retrieval
- speech recognition
- retrieval model
- statistical language models
- query expansion
- language modelling
- context sensitive
- vector space model
- relevance model
- document ranking
- text retrieval
- pseudo relevance feedback
- smoothing methods
- test collection
- word error rate
- ad hoc information retrieval
- language models for information retrieval
- language model for information retrieval
- machine learning
- translation model
- document length
- pseudo feedback
- search engine