Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections.
Yuanpu CaoBochuan CaoJinghui ChenPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- information retrieval
- document retrieval
- probabilistic model
- n gram
- speech recognition
- retrieval model
- language modelling
- query expansion
- language model for information retrieval
- smoothing methods
- test collection
- ad hoc information retrieval
- pseudo relevance feedback
- statistical language models
- language models for information retrieval
- vector space model
- context sensitive
- query terms
- relevance model
- document ranking
- query specific
- word error rate
- statistical language modeling