Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory.
Niloofar MireshghallahHyunwoo KimXuhui ZhouYulia TsvetkovMaarten SapReza ShokriYejin ChoiPublished in: ICLR (2024)
Keyphrases
- language model
- language modeling
- context sensitive
- probabilistic model
- language modelling
- n gram
- speech recognition
- document retrieval
- information retrieval
- ad hoc information retrieval
- statistical language models
- query expansion
- retrieval model
- smoothing methods
- vector space model
- pseudo relevance feedback
- contextual information
- query terms
- word error rate
- test collection
- privacy preserving
- language model for information retrieval
- statistical language modeling
- language models for information retrieval