Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models.
Jie ChenXintian HanYu MaXun ZhouLiang XiangPublished in: CoRR (2024)
Keyphrases
- language model
- fine tuning
- reinforcement learning
- supervised learning
- language modeling
- fine tuned
- viable alternative
- document retrieval
- language modelling
- n gram
- query expansion
- learning algorithm
- probabilistic model
- information retrieval
- retrieval model
- speech recognition
- statistical language models
- test collection
- smoothing methods
- ad hoc information retrieval
- semi supervised
- pseudo relevance feedback
- machine learning
- document length
- context sensitive
- vector space model
- language model for information retrieval
- query terms
- document ranking
- translation model
- passage retrieval
- relevance model
- retrieval effectiveness
- text mining
- training set
- feature selection