Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models.
Ashutosh BahetiXiming LuFaeze BrahmanRonan Le BrasMaarten SapMark O. RiedlPublished in: ICLR (2024)
Keyphrases
- language model
- reinforcement learning
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- query expansion
- language modelling
- retrieval model
- information retrieval
- statistical language models
- language models for information retrieval
- test collection
- context sensitive
- query terms
- relevance model
- document ranking
- word error rate
- smoothing methods
- ad hoc information retrieval
- machine learning
- vector space model
- translation model
- document length
- learning algorithm
- statistical language modeling