Universal and Transferable Adversarial Attacks on Aligned Language Models.
Andy ZouZifan WangJ. Zico KolterMatt FredriksonPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- query expansion
- n gram
- language modelling
- retrieval model
- information retrieval
- document retrieval
- speech recognition
- test collection
- context sensitive
- vector space model
- query terms
- ad hoc information retrieval
- document ranking
- smoothing methods
- pseudo relevance feedback
- statistical language models
- language model for information retrieval
- translation model
- word error rate
- relevance model
- hidden markov models
- language modeling approaches
- image retrieval