Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models.
Xudong LuQi LiuYuhui XuAojun ZhouSiyuan HuangBo ZhangJunchi YanHongsheng LiPublished in: CoRR (2024)
Keyphrases
- language model
- mixture model
- domain experts
- n gram
- language modeling
- language modelling
- probabilistic model
- information retrieval
- query expansion
- machine learning
- context sensitive
- vector space model
- expert finding
- language model for information retrieval
- document collections
- generative model
- test collection
- retrieval model
- feature selection
- statistical language models