Large Language Model Unlearning via Embedding-Corrupted Prompts.
Chris Yuhao LiuYaxuan WangJeffrey FlaniganYang LiuPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- speech recognition
- retrieval model
- information retrieval
- query expansion
- mixture model
- query terms
- vector space
- ad hoc information retrieval
- language modelling
- test collection
- statistical language models
- context sensitive
- vector space model
- pseudo relevance feedback
- smoothing methods
- word error rate
- translation model
- multiword
- query specific
- dependency structure
- text classification