PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.
Neal MangaokarAshish HoodaJihye ChoiShreyas ChandrashekaranKassem FawazSomesh JhaAtul PrakashPublished in: CoRR (2024)
Keyphrases
- language model
- document ranking
- language modeling
- n gram
- document retrieval
- information retrieval
- probabilistic model
- language modelling
- speech recognition
- retrieval model
- query expansion
- test collection
- context sensitive
- relevance model
- statistical language models
- mixture model
- query terms
- vector space model
- smoothing methods
- passage retrieval
- pseudo relevance feedback
- ad hoc information retrieval
- language models for information retrieval
- web search engines
- generative model
- word clouds
- language model for information retrieval