Language Model Self-improvement by Reinforcement Learning Contemplation.
Jing-Cheng PangPengyuan WangKaiyuan LiXiong-Hui ChenJiacheng XuZongzhang ZhangYang YuPublished in: ICLR (2024)
Keyphrases
- language model
- reinforcement learning
- language modeling
- n gram
- probabilistic model
- language modelling
- speech recognition
- retrieval model
- document retrieval
- information retrieval
- query expansion
- mixture model
- test collection
- context sensitive
- statistical language models
- smoothing methods
- pseudo relevance feedback
- translation model
- document ranking
- relevance model
- machine learning
- vector space model
- query terms
- multiword
- document length
- ad hoc information retrieval