LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models.
Liang ZhaoTianwen WeiLiang ZengCheng ChengLiu YangPeng ChengLijie WangChenxia LiXuejie WuBo ZhuYimeng GanRui HuShuicheng YanHan FangYahui ZhouPublished in: CoRR (2024)
Keyphrases
- language model
- context sensitive
- language modeling
- probabilistic model
- n gram
- speech recognition
- document retrieval
- retrieval model
- information retrieval
- query expansion
- language modelling
- statistical language models
- ad hoc information retrieval
- language model for information retrieval
- smoothing methods
- vector space model
- relevance model
- query terms
- test collection
- pseudo relevance feedback
- context dependent
- document length
- web search
- okapi bm