Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content.
Federico BianchiJames ZouPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- document retrieval
- n gram
- information retrieval
- speech recognition
- security risks
- query expansion
- test collection
- language modelling
- retrieval model
- ad hoc information retrieval
- smoothing methods
- statistical language models
- word clouds
- language model for information retrieval
- document ranking
- query terms
- multimedia
- pseudo relevance feedback
- context sensitive
- passage retrieval
- vector space model
- retrieval effectiveness
- okapi bm
- language models for information retrieval