Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yuan, Hongyi, Lu, Keming, Huang, Fei, Yuan, Zheng, Zhou, Chang
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2311.08981
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911795549044736
author Yuan, Hongyi
Lu, Keming
Huang, Fei
Yuan, Zheng
Zhou, Chang
author_facet Yuan, Hongyi
Lu, Keming
Huang, Fei
Yuan, Zheng
Zhou, Chang
contents Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative decoding and contrastive decoding, we introduce Speculative Contrastive Decoding~(SCD), a straightforward yet powerful decoding approach that leverages predictions from smaller language models~(LMs) to achieve both decoding acceleration and quality improvement. Extensive evaluations and analyses on four diverse language tasks demonstrate the effectiveness of SCD, showing that decoding efficiency and quality can compatibly benefit from one smaller LM.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08981
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Speculative Contrastive Decoding
Yuan, Hongyi
Lu, Keming
Huang, Fei
Yuan, Zheng
Zhou, Chang
Computation and Language
Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative decoding and contrastive decoding, we introduce Speculative Contrastive Decoding~(SCD), a straightforward yet powerful decoding approach that leverages predictions from smaller language models~(LMs) to achieve both decoding acceleration and quality improvement. Extensive evaluations and analyses on four diverse language tasks demonstrate the effectiveness of SCD, showing that decoding efficiency and quality can compatibly benefit from one smaller LM.
title Speculative Contrastive Decoding
topic Computation and Language
url https://arxiv.org/abs/2311.08981