SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors.
Tinghao XieXiangyu QiYi ZengYangsibo HuangUdari Madhushani SehwagKaixuan HuangLuxi HeBoyi WeiDacheng LiYing ShengRuoxi JiaBo LiKai LiDanqi ChenPeter HendersonPrateek MittalPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- information retrieval
- language modelling
- speech recognition
- test collection
- document retrieval
- query expansion
- retrieval model
- ad hoc information retrieval
- smoothing methods
- context sensitive
- statistical language models
- translation model
- mixture model
- pseudo relevance feedback
- query terms
- information retrieval systems
- relevance model
- statistical machine translation