Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Xiangyu QiYi ZengTinghao XiePin-Yu ChenRuoxi JiaPrateek MittalPeter HendersonPublished in: ICLR (2024)
Keyphrases
- language model
- fine tuning
- language modeling
- document retrieval
- n gram
- language modelling
- statistical language models
- speech recognition
- probabilistic model
- test collection
- viable alternative
- retrieval model
- information retrieval
- query expansion
- vector space model
- fine tuned
- context sensitive
- document ranking
- recommender systems
- relevance model
- passage retrieval
- query terms
- text categorization
- language model for information retrieval
- pseudo relevance feedback
- image content
- smoothing methods
- collaborative filtering
- statistical language modeling
- language models for information retrieval