Adversarial Contrastive Decoding: Boosting Safety Alignment of Large Language Models via Opposite Prompt Optimization.
Zhengyue ZhaoXiaoyun ZhangKaidi XuXing HuRui ZhangZidong DuQi GuoYunji ChenPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- information retrieval
- probabilistic model
- retrieval model
- language modelling
- statistical language models
- ad hoc information retrieval
- speech recognition
- test collection
- vector space model
- language model for information retrieval
- context sensitive
- query expansion
- relevance model
- query terms
- document ranking
- smoothing methods
- word error rate
- retrieval effectiveness
- pseudo relevance feedback
- language models for information retrieval
- machine learning
- cross lingual
- term dependencies
- document length
- okapi bm
- feature selection