Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic.
Rishabh BhardwajDo Duc AnhSoujanya PoriaPublished in: ACL (1) (2024)
Keyphrases
- language model
- language modeling
- fine tuned
- document retrieval
- probabilistic model
- n gram
- speech recognition
- information retrieval
- query expansion
- retrieval model
- language modelling
- context sensitive
- fine tuning
- ad hoc information retrieval
- test collection
- query terms
- vector space model
- smoothing methods
- language model for information retrieval
- relevance model
- translation model
- passage retrieval
- word error rate
- active learning