LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models.
Huiqiang JiangQianhui WuChin-Yew LinYuqing YangLili QiuPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- information retrieval
- document retrieval
- language modelling
- speech recognition
- probabilistic model
- statistical language models
- query expansion
- retrieval model
- context sensitive
- mixture model
- pseudo relevance feedback
- test collection
- query terms
- smoothing methods
- language models for information retrieval
- bayesian networks
- word error rate
- vector space model
- document length
- ad hoc information retrieval
- active learning
- language model for information retrieval