Composite Backdoor Attacks Against Large Language Models.
Hai HuangZhengyu ZhaoMichael BackesYun ShenYang ZhangPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- retrieval model
- language modelling
- document retrieval
- probabilistic model
- speech recognition
- test collection
- query expansion
- information retrieval
- context sensitive
- statistical language models
- vector space model
- ad hoc information retrieval
- smoothing methods
- word error rate
- language models for information retrieval
- query terms
- pseudo relevance feedback
- relevance model
- document ranking
- query specific
- machine learning
- document length