Sketch: A Toolkit for Streamlining LLM Operations

Bibliographic Details
Title:	Sketch: A Toolkit for Streamlining LLM Operations
Authors:	Jiang, Xin, Li, Xiang, Ma, Wenjia, Fang, Xuezhi, Yao, Yiqun, Yu, Naitong, Meng, Xuying, Han, Peng, Li, Jing, Sun, Aixin, Wang, Yequan
Publication Year:	2024
Collection:	Computer Science
Subject Terms:	Computer Science - Computation and Language, Computer Science - Artificial Intelligence
More Details:	Large language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks through a generative approach. However, the flexibility of their output format poses challenges in controlling and harnessing the model's outputs, thereby constraining the application of LLMs in various domains. In this work, we present Sketch, an innovative toolkit designed to streamline LLM operations across diverse fields. Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks; (2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks; (3) an open-source dataset for output format control, along with tools for dataset construction; and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions. We anticipate this initiative to bring considerable convenience to LLM users, achieving the goal of ''plug-and-play'' for various applications. The components of Sketch will be progressively open-sourced at https://github.com/cofe-ai/Sketch.
Document Type:	Working Paper
Access URL:	http://arxiv.org/abs/2409.03346
Accession Number:	edsarx.2409.03346
Database:	arXiv

FullText	Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2409.03346 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240905&spage=&pages=&title=Sketch: A Toolkit for Streamlining LLM Operations&atitle=Sketch%3A%20A%20Toolkit%20for%20Streamlining%20LLM%20Operations&aulast=Jiang%2C%20Xin&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries
Header	DbId: edsarx DbLabel: arXiv An: edsarx.2409.03346 RelevancyScore: 1112 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1112.255859375
IllustrationInfo
Items	– Name: Title Label: Title Group: Ti Data: Sketch: A Toolkit for Streamlining LLM Operations – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Jiang%2C+Xin%22">Jiang, Xin</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Xiang%22">Li, Xiang</searchLink><br /><searchLink fieldCode="AR" term="%22Ma%2C+Wenjia%22">Ma, Wenjia</searchLink><br /><searchLink fieldCode="AR" term="%22Fang%2C+Xuezhi%22">Fang, Xuezhi</searchLink><br /><searchLink fieldCode="AR" term="%22Yao%2C+Yiqun%22">Yao, Yiqun</searchLink><br /><searchLink fieldCode="AR" term="%22Yu%2C+Naitong%22">Yu, Naitong</searchLink><br /><searchLink fieldCode="AR" term="%22Meng%2C+Xuying%22">Meng, Xuying</searchLink><br /><searchLink fieldCode="AR" term="%22Han%2C+Peng%22">Han, Peng</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Jing%22">Li, Jing</searchLink><br /><searchLink fieldCode="AR" term="%22Sun%2C+Aixin%22">Sun, Aixin</searchLink><br /><searchLink fieldCode="AR" term="%22Wang%2C+Yequan%22">Wang, Yequan</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computation+and+Language%22">Computer Science - Computation and Language</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink> – Name: Abstract Label: Description Group: Ab Data: Large language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks through a generative approach. However, the flexibility of their output format poses challenges in controlling and harnessing the model's outputs, thereby constraining the application of LLMs in various domains. In this work, we present Sketch, an innovative toolkit designed to streamline LLM operations across diverse fields. Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks; (2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks; (3) an open-source dataset for output format control, along with tools for dataset construction; and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions. We anticipate this initiative to bring considerable convenience to LLM users, achieving the goal of ''plug-and-play'' for various applications. The components of Sketch will be progressively open-sourced at https://github.com/cofe-ai/Sketch. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2409.03346" linkWindow="_blank">http://arxiv.org/abs/2409.03346</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2409.03346
PLink	https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2409.03346
RecordInfo	BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computation and Language Type: general – SubjectFull: Computer Science - Artificial Intelligence Type: general Titles: – TitleFull: Sketch: A Toolkit for Streamlining LLM Operations Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Jiang, Xin – PersonEntity: Name: NameFull: Li, Xiang – PersonEntity: Name: NameFull: Ma, Wenjia – PersonEntity: Name: NameFull: Fang, Xuezhi – PersonEntity: Name: NameFull: Yao, Yiqun – PersonEntity: Name: NameFull: Yu, Naitong – PersonEntity: Name: NameFull: Meng, Xuying – PersonEntity: Name: NameFull: Han, Peng – PersonEntity: Name: NameFull: Li, Jing – PersonEntity: Name: NameFull: Sun, Aixin – PersonEntity: Name: NameFull: Wang, Yequan IsPartOfRelationships: – BibEntity: Dates: – D: 05 M: 09 Type: published Y: 2024
ResultId	1