"According to ..." Prompting Language Models Improves Quoting from Pre-Training Data.
Orion WellerMarc MaroneNathaniel WeirDawn J. LawrieDaniel KhashabiBenjamin Van DurmePublished in: CoRR (2023)
Keyphrases
- language model
- training data
- language modeling
- n gram
- query expansion
- speech recognition
- probabilistic model
- information retrieval
- document retrieval
- statistical language models
- language modelling
- retrieval model
- context sensitive
- supervised learning
- decision trees
- training set
- learning algorithm
- query terms
- test collection
- translation model
- language models for information retrieval
- vector space model
- smoothing methods
- classification accuracy
- ad hoc information retrieval
- relevance model
- word error rate
- error rate
- pseudo relevance feedback
- document ranking
- query specific
- labeled data