ALANCA: Active Learning Guided Adversarial Attacks for Code Comprehension on Diverse Pre-trained and Large Language Models.
Dexin LiuShikun ZhangPublished in: SANER (2024)
Keyphrases
- language model
- pre trained
- active learning
- training examples
- language modeling
- training data
- speech recognition
- document retrieval
- n gram
- information retrieval
- probabilistic model
- language modelling
- query expansion
- statistical language models
- training set
- learning algorithm
- semi supervised
- language models for information retrieval
- supervised learning
- small number
- unlabeled data
- test collection
- retrieval model
- smoothing methods
- machine learning
- learning process
- labeled data
- document ranking
- relevance feedback
- control signals
- semi supervised learning
- generative model
- relevance model
- information extraction