Teaching Large Language Models to Reason with Reinforcement Learning.
Alex HavrillaYuqing DuSharath Chandra RaparthyChristoforos NalmpantisJane Dwivedi-YuMaksym ZhuravinskyiEric HambroSainbayar SukhbaatarRoberta RaileanuPublished in: CoRR (2024)
Keyphrases
- language model
- reinforcement learning
- language modeling
- learning process
- document retrieval
- retrieval model
- probabilistic model
- information retrieval
- n gram
- query expansion
- language modelling
- test collection
- statistical language models
- smoothing methods
- ad hoc information retrieval
- speech recognition
- context sensitive
- pseudo relevance feedback
- language models for information retrieval
- learning algorithm
- document ranking
- language model for information retrieval
- translation model
- passage retrieval
- word error rate
- query terms
- retrieval systems
- statistical language modeling
- information extraction
- machine learning