PrefCLM: Enhancing Preference-based Reinforcement Learning with Crowdsourced Large Language Models.
Ruiqi WangDezhong ZhaoZiqin YuanIke ObiByung-Cheol MinPublished in: CoRR (2024)
Keyphrases
- language model
- reinforcement learning
- language modeling
- test collection
- document retrieval
- probabilistic model
- information retrieval
- speech recognition
- n gram
- retrieval model
- query expansion
- language modelling
- ad hoc information retrieval
- language models for information retrieval
- statistical language models
- smoothing methods
- query terms
- context sensitive
- learning algorithm
- pseudo relevance feedback
- translation model
- document ranking
- machine learning
- hidden markov models
- retrieval effectiveness
- query specific
- language model for information retrieval
- passage retrieval
- transfer learning
- co occurrence