ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models.
Yash AkhauriAhmed F. AbouElhamayedJordan DotzelZhiru ZhangAlexander M. RushSafeen HudaMohamed S. AbdelfattahPublished in: CoRR (2024)
Keyphrases
- language model
- context sensitive
- language modeling
- probabilistic model
- contextual information
- n gram
- information retrieval
- speech recognition
- language modelling
- document retrieval
- retrieval model
- test collection
- query expansion
- query terms
- statistical language models
- ad hoc information retrieval
- smoothing methods
- high dimensional
- document length
- passage retrieval
- term dependencies
- relevance model
- pseudo relevance feedback
- language models for information retrieval
- document ranking
- word error rate
- vector space model
- retrieval effectiveness