Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge.
Weikai LuZiqian ZengJianwei WangZhengdong LuZelin ChenHuiping ZhuangCen ChenPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- language modelling
- document retrieval
- retrieval model
- query expansion
- statistical language models
- vector space model
- information retrieval
- context sensitive
- smoothing methods
- knowledge discovery
- machine learning
- language models for information retrieval
- query terms
- test collection
- semantic information
- automatic speech recognition
- relevance model
- word error rate