Dual-Assessment Driven Pruning: Iterative Optimizing Layer-wise Sparsity for Large Language Model.
Qinghui SunWeilun WangYanni ZhuShenghuan HeHao YiZehua CaiHong LiuPublished in: KDD (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- language modelling
- speech recognition
- query expansion
- test collection
- retrieval model
- mixture model
- context sensitive
- pairwise
- translation model
- high dimensional
- information retrieval
- ad hoc information retrieval
- pseudo relevance feedback
- statistical language models
- smoothing methods
- word clouds
- vector space model
- relevance model
- document length
- co occurrence