Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.
Federico BianchiMirac SuzgunGiuseppe AttanasioPaul RöttgerDan JurafskyTatsunori HashimotoJames ZouPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- information retrieval
- document retrieval
- retrieval model
- statistical language models
- n gram
- language modelling
- speech recognition
- language model for information retrieval
- smoothing methods
- query expansion
- ad hoc information retrieval
- collaborative filtering
- vector space model
- document ranking
- context sensitive
- test collection
- document length