D2O: Dynamic Discriminative Operations for Efficient Generative Inference of Large Language Models.
Zhongwei WanXinjian WuYu ZhangYi XinChaofan TaoZhihong ZhuXin WangSiqi LuoJing XiongMi ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- statistical language models
- query expansion
- language modelling
- retrieval model
- mixture model
- discriminative learning
- speech recognition
- context sensitive
- test collection
- unsupervised learning
- relevance model
- smoothing methods
- language models for information retrieval
- information retrieval
- vector space model
- query terms
- bayesian networks
- translation model
- error rate
- generative model
- document length
- language modeling framework
- search engine