LLMs as Counterfactual Explanation Modules: Can ChatGPT Explain Black-box Text Classifiers?
Amrita BhattacharjeeRaha MoraffahJoshua GarlandHuan LiuPublished in: CoRR (2023)
Keyphrases
- black box
- text classifiers
- text classification
- text categorization
- naive bayes
- white box
- black boxes
- document classification
- labeled documents
- text data
- integration testing
- test cases
- svm classifier
- feature selection
- semantic features
- training data
- artificial intelligence
- labeled data
- relational databases
- web pages
- white box testing