Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy.
Daphne IppolitoFlorian TramèrMilad NasrChiyuan ZhangMatthew JagielskiKatherine LeeChristopher A. Choquette-ChooNicholas CarliniPublished in: CoRR (2022)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- information retrieval
- speech recognition
- probabilistic model
- query expansion
- retrieval model
- test collection
- ad hoc information retrieval
- statistical language models
- language modelling
- vector space model
- smoothing methods
- context sensitive
- query terms
- query specific
- pseudo relevance feedback
- translation model
- document ranking
- relevance model
- word error rate
- language models for information retrieval
- term dependencies