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: ACL (1) (2024)
Keyphrases
- language model
- mixture model
- language modeling
- n gram
- expert finding
- information retrieval
- probabilistic model
- domain experts
- speech recognition
- document retrieval
- machine learning
- language modelling
- test collection
- retrieval model
- language models for information retrieval
- document ranking
- context sensitive
- query terms
- retrieval effectiveness
- term dependencies
- smoothing methods
- document collections
- ad hoc information retrieval
- bayesian networks
- language model for information retrieval