ReaLHF: Optimized RLHF Training for Large Language Models through Parameter Reallocation.
Zhiyu MeiWei FuKaiwei LiGuangju WangHuanchen ZhangYi WuPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- retrieval model
- speech recognition
- information retrieval
- language modelling
- ad hoc information retrieval
- smoothing methods
- query expansion
- test collection
- training set
- language models for information retrieval
- translation model
- statistical language models
- vector space model
- context sensitive
- document ranking
- word error rate
- query terms
- term dependencies
- cross lingual
- document length
- text retrieval
- language model for information retrieval