Accelerating Retrieval-Augmented Language Model Serving with Speculation.
Zhihao ZhangAlan ZhuLijie YangYihua XuLanting LiPhitchaya Mangpo PhothilimthanaZhihao JiaPublished in: CoRR (2024)
Keyphrases
- language model
- retrieval model
- document retrieval
- ad hoc information retrieval
- query expansion
- test collection
- information retrieval
- language modeling
- language models for information retrieval
- query terms
- document length
- cross language retrieval
- n gram
- statistical language models
- query specific
- web page retrieval
- relevance model
- probabilistic model
- smoothing methods
- trec test collections
- context sensitive
- jelinek mercer
- mixture model
- document level
- language modelling
- vector space model
- term dependencies
- text retrieval
- document ranking
- pseudo relevance feedback
- speech recognition
- ir models
- statistical language modeling
- retrieval effectiveness
- okapi bm
- translation model
- pseudo feedback
- word clouds
- language model for information retrieval
- ad hoc retrieval
- probabilistic retrieval models
- retrieval process
- average precision
- retrieval systems
- information retrieval systems
- term frequency
- tf idf
- cross language
- image database
- relevance feedback
- term weighting
- divergence from randomness
- inter document similarities
- original query
- retrieval method
- keywords