Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making.
Xuanjie FangSijie ChengYang LiuWei WangPublished in: ACL (Findings) (2023)
Keyphrases
- language model
- sequential decision making
- pre trained
- language modeling
- n gram
- probabilistic model
- speech recognition
- information retrieval
- language modelling
- decision problems
- language models for information retrieval
- query expansion
- statistical language modeling
- retrieval model
- statistical language models
- smoothing methods
- influence diagrams
- reinforcement learning
- relevance model
- data sets
- high dimensional
- training examples
- graphical models
- training data
- bayesian networks
- text classification