Inference acceleration for large language models using "stairs" assisted greedy generation.
Domas GrigaliunasMantas LukoseviciusPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- language modelling
- information retrieval
- speech recognition
- vector space model
- query expansion
- test collection
- retrieval model
- smoothing methods
- mixture model
- statistical language models
- context sensitive
- pseudo relevance feedback
- ad hoc information retrieval
- language model for information retrieval
- document ranking
- query terms
- language models for information retrieval
- machine learning
- retrieval effectiveness
- web documents
- text mining
- okapi bm
- feature selection