On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference.
Siyu RenKenny Q. ZhuPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- speech recognition
- mixture model
- query expansion
- information retrieval
- document retrieval
- generative model
- language modelling
- retrieval model
- context sensitive
- ad hoc information retrieval
- language model for information retrieval
- smoothing methods
- statistical language models
- bayesian inference
- vector space model
- relevance model
- bayesian networks
- language modeling framework
- unsupervised learning
- word error rate
- test collection
- query terms
- statistical machine translation
- translation model
- query specific
- document ranking
- document length
- pseudo relevance feedback
- co occurrence
- language models for information retrieval
- retrieval effectiveness