PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models.
Hongwei YaoJian LouZhan QinPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- information retrieval
- speech recognition
- test collection
- retrieval model
- probabilistic model
- query expansion
- context sensitive
- vector space model
- language modelling
- smoothing methods
- ad hoc information retrieval
- statistical language models
- translation model
- query specific
- query terms
- statistical language modeling
- term dependencies
- passage retrieval
- pseudo relevance feedback
- retrieval effectiveness
- relevance model
- information retrieval systems
- language models for information retrieval