One-Shot Safety Alignment for Large Language Models via Optimal Dualization.
Xinmeng HuangShuo LiEdgar DobribanOsbert BastaniHamed HassaniDongsheng DingPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- query expansion
- language modelling
- statistical language models
- information retrieval
- retrieval model
- context sensitive
- document retrieval
- speech recognition
- test collection
- smoothing methods
- vector space model
- pseudo relevance feedback
- language model for information retrieval
- language models for information retrieval
- ad hoc information retrieval
- document ranking
- passage retrieval
- relevance model
- question answering