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