Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots.
Ruixiang (Ryan) TangJiayi YuanYiming LiZirui LiuRui ChenXia HuPublished in: NeurIPS (2023)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- retrieval model
- speech recognition
- document retrieval
- query expansion
- language modelling
- information retrieval
- test collection
- context sensitive
- statistical language models
- vector space model
- document ranking
- smoothing methods
- ad hoc information retrieval
- query terms
- translation model
- okapi bm
- relevance model
- tf idf
- retrieval effectiveness
- decision trees