Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Xiangyu QiYi ZengTinghao XiePin-Yu ChenRuoxi JiaPrateek MittalPeter HendersonPublished in: CoRR (2023)
Keyphrases
- language model
- fine tuning
- language modeling
- n gram
- language modelling
- probabilistic model
- document retrieval
- information retrieval
- query expansion
- speech recognition
- test collection
- statistical language models
- retrieval model
- smoothing methods
- viable alternative
- query terms
- recommender systems
- ad hoc information retrieval
- language model for information retrieval
- fine tuned
- passage retrieval
- relevance model
- vector space model
- information seeking
- translation model
- user ratings
- term dependencies
- context sensitive
- retrieval effectiveness
- language models for information retrieval
- bayesian networks