Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models.
Yang BaiGe PeiJindong GuYong YangXingjun MaPublished in: CoRR (2024)
Keyphrases
- language model
- data extraction
- language modeling
- n gram
- web data extraction
- semi structured
- probabilistic model
- document retrieval
- information retrieval
- speech recognition
- query expansion
- data integration
- language modelling
- retrieval model
- statistical language models
- test collection
- language models for information retrieval
- smoothing methods
- databases
- web pages
- query terms
- pseudo relevance feedback
- information extraction
- relevance model
- translation model
- structured data
- text classification
- natural language processing
- web databases
- association rules