Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint.
Zhipeng ChenKun ZhouWayne Xin ZhaoJunchen WanFuzheng ZhangDi ZhangJi-Rong WenPublished in: CoRR (2024)
Keyphrases
- fine grained
- language model
- reinforcement learning
- language modeling
- coarse grained
- document retrieval
- n gram
- speech recognition
- information retrieval
- probabilistic model
- access control
- retrieval model
- language modelling
- statistical language models
- query terms
- vector space model
- language models for information retrieval
- document ranking
- query expansion
- test collection
- smoothing methods
- pseudo relevance feedback
- machine learning
- context sensitive
- improving web search
- search engine
- transfer learning