Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology.
Zhenhua WangWei XieBaosheng WangEnze WangZhiwen GuiShuoyoucheng MaKai ChenPublished in: CoRR (2024)
Keyphrases
- language model
- cognitive psychology
- language modeling
- n gram
- probabilistic model
- retrieval model
- information retrieval
- intelligent systems
- speech recognition
- language modelling
- statistical language models
- document retrieval
- cognitive architecture
- test collection
- artificial intelligence
- query expansion
- context sensitive
- mixture model
- query terms
- ad hoc information retrieval
- smoothing methods
- translation model
- cognitive science
- relevance model
- bayesian networks
- computational linguistics
- document length
- machine learning
- data mining