Secrets of RLHF in Large Language Models Part II: Reward Modeling.
Binghai WangRui ZhengLu ChenYan LiuShihan DouCaishuang HuangWei ShenSenjie JinEnyu ZhouChenyu ShiSongyang GaoNuo XuYuhao ZhouXiaoran FanZhiheng XiJun ZhaoXiao WangTao JiHang YanLixing ShenZhan ChenTao GuiQi ZhangXipeng QiuXuanjing HuangZuxuan WuYu-Gang JiangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- probabilistic model
- retrieval model
- language modelling
- test collection
- statistical language models
- query expansion
- language model for information retrieval
- information retrieval
- context sensitive
- query terms
- relevance model
- statistical language modeling
- pseudo relevance feedback
- smoothing methods
- vector space model
- ad hoc information retrieval
- language models for information retrieval
- query specific
- term dependencies
- text mining
- document length
- bayesian networks