RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment.
Kevin YangDan KleinAsli CelikyilmazNanyun PengYuandong TianPublished in: CoRR (2023)
Keyphrases
- language model
- reinforcement learning
- language modeling
- n gram
- document retrieval
- query expansion
- speech recognition
- information retrieval
- probabilistic model
- context sensitive
- language modelling
- retrieval model
- mixture model
- test collection
- statistical language models
- ad hoc information retrieval
- vector space model
- relevance model
- translation model
- document ranking
- query specific
- pseudo feedback
- machine learning
- statistical machine translation
- smoothing methods
- pseudo relevance feedback
- word error rate
- query terms
- word clouds
- language model for information retrieval