Training Data Extraction From Pre-trained Language Models: A Survey.
Shotaro IshiharaPublished in: CoRR (2023)
Keyphrases
- language model
- pre trained
- training data
- language modeling
- training examples
- n gram
- probabilistic model
- document retrieval
- information retrieval
- speech recognition
- language modelling
- learning algorithm
- training set
- test collection
- query expansion
- retrieval model
- data sets
- statistical language models
- language models for information retrieval
- training samples
- smoothing methods
- information extraction
- decision trees
- document ranking
- labeled data
- prior knowledge
- neural network
- semi supervised learning
- multi modal
- dimensionality reduction
- supervised learning
- hidden markov models
- control signals
- high dimensional