Towards Effective and Efficient Continual Pre-training of Large Language Models.
Jie ChenZhipeng ChenJiapeng WangKun ZhouYutao ZhuJinhao JiangYingqian MinWayne Xin ZhaoZhicheng DouJiaxin MaoYankai LinRuihua SongJun XuXu ChenRui YanZhewei WeiDi HuWenbing HuangJi-Rong WenPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- statistical language models
- n gram
- retrieval model
- speech recognition
- language modelling
- test collection
- information retrieval
- ad hoc information retrieval
- smoothing methods
- query expansion
- document retrieval
- document ranking
- vector space model
- training set
- relevance model
- passage retrieval
- co occurrence
- query specific
- information extraction
- word error rate
- bayesian networks
- search engine