How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
Xinshuai DongAnh Tuan LuuMin LinShuicheng YanHanwang ZhangPublished in: NeurIPS (2021)
Keyphrases
- language model
- pre trained
- fine tuned
- language modeling
- fine tuning
- n gram
- document retrieval
- speech recognition
- training data
- information retrieval
- retrieval model
- query expansion
- probabilistic model
- language modelling
- statistical language models
- control signals
- test collection
- domain specific
- language models for information retrieval
- training examples
- relevance model
- smoothing methods
- face recognition
- decision trees
- machine learning
- data sets