Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models.
Xi LiYusen ZhangRenze LouChen WuJiaqi WangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- information retrieval
- retrieval model
- language modelling
- statistical language models
- query expansion
- test collection
- context sensitive
- document ranking
- smoothing methods
- language models for information retrieval
- pseudo relevance feedback
- relevance model
- ad hoc information retrieval
- language model for information retrieval
- word error rate
- translation model
- passage retrieval
- query terms
- pseudo feedback
- okapi bm
- error rate
- clustering algorithm
- language modeling approaches
- search engine