Elephants Never Forget: Testing Language Models for Memorization of Tabular Data.
Sebastian BordtHarsha NoriRich CaruanaPublished in: CoRR (2024)
Keyphrases
- language model
- tabular data
- language modeling
- n gram
- probabilistic model
- speech recognition
- controlled tabular adjustment
- statistical language models
- query expansion
- information retrieval
- cell suppression
- document retrieval
- language modelling
- language models for information retrieval
- smoothing methods
- retrieval model
- query terms
- differential privacy
- test collection
- relevance model
- cluster analysis
- document ranking
- translation model
- data model
- digital libraries
- database systems