Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding.
Sangmin BaeJongwoo KoHwanjun SongSe-Young YunPublished in: EMNLP (2023)
Keyphrases
- language model
- autoregressive
- probabilistic model
- language modeling
- document retrieval
- non stationary
- speech recognition
- information retrieval
- relevance model
- retrieval model
- model selection
- n gram
- statistical language models
- moving average
- gaussian markov random field
- language modelling
- test collection
- bayesian networks