H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
Zhenyu ZhangYing ShengTianyi ZhouTianlong ChenLianmin ZhengRuisi CaiZhao SongYuandong TianChristopher RéClark W. BarrettZhangyang WangBeidi ChenPublished in: NeurIPS (2023)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- test collection
- query expansion
- document retrieval
- statistical language models
- probabilistic model
- language modelling
- ad hoc information retrieval
- relevance model
- language model for information retrieval
- language models for information retrieval
- translation model
- vector space model
- context sensitive
- retrieval model
- mixture model
- information retrieval
- passage retrieval
- query terms