Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences.
Corby RossetChing-An ChengArindam MitraMichael SantacroceAhmed AwadallahTengyang XiePublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- query expansion
- speech recognition
- document retrieval
- statistical language models
- language modelling
- context sensitive
- smoothing methods
- language model for information retrieval
- information retrieval
- ad hoc information retrieval
- retrieval model
- pseudo relevance feedback
- query terms
- test collection
- relevance model
- document ranking
- document collections