Salvato in:
Dettagli Bibliografici
Autori principali: Li, Beibin, Zhang, Yi, Bubeck, Sébastien, Pathuri, Jeevan, Menache, Ishai
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.20347
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909213548085248
author Li, Beibin
Zhang, Yi
Bubeck, Sébastien
Pathuri, Jeevan
Menache, Ishai
author_facet Li, Beibin
Zhang, Yi
Bubeck, Sébastien
Pathuri, Jeevan
Menache, Ishai
contents We study the efficacy of Small Language Models (SLMs) in facilitating application usage through natural language interactions. Our focus here is on a particular internal application used in Microsoft for cloud supply chain fulfilment. Our experiments show that small models can outperform much larger ones in terms of both accuracy and running time, even when fine-tuned on small datasets. Alongside these results, we also highlight SLM-based system design considerations.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20347
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Small Language Models for Application Interactions: A Case Study
Li, Beibin
Zhang, Yi
Bubeck, Sébastien
Pathuri, Jeevan
Menache, Ishai
Computation and Language
Artificial Intelligence
Machine Learning
We study the efficacy of Small Language Models (SLMs) in facilitating application usage through natural language interactions. Our focus here is on a particular internal application used in Microsoft for cloud supply chain fulfilment. Our experiments show that small models can outperform much larger ones in terms of both accuracy and running time, even when fine-tuned on small datasets. Alongside these results, we also highlight SLM-based system design considerations.
title Small Language Models for Application Interactions: A Case Study
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.20347