CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming

Li Feng; Ryan Yen; Yuzhe You; Mingming Fan; Jian Zhao; Zhicong Lu

doi:10.1145/3613904.3642212

CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming

Li Feng, Ryan Yen, Yuzhe You, Mingming Fan, Jian Zhao, Zhicong Lu

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

8 Citations (Scopus)

Abstract

Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and context-switching among programmers from varying backgrounds. However, programmers may face challenges during prompt engineering in a collaborative setting as they need to actively keep aware of their collaborators' progress and intents. In this paper, we aim to investigate ways to assist programmers' prompt engineering in a collaborative context. We first conducted a formative study to understand the workflows and challenges of programmers when using NL for collaborative programming. Based on our findings, we implemented a prototype, CoPrompt, to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. Our user study indicates that CoPrompt assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs. © 2024 Copyright held by the owner/author(s)

Original language	English
Title of host publication	CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems
Publisher	Association for Computing Machinery
ISBN (Print)	9798400703300
DOIs	https://doi.org/10.1145/3613904.3642212
Publication status	Published - May 2024
Event	2024 CHI Conference on Human Factors in Computing Sytems (CHI 2024): "Surfing the World" - Hawaiʻi Convention Center, Honolulu, United States Duration: 11 May 2024 → 16 May 2024 https://chi2024.acm.org/for-attendees/

Publication series

Name	Conference on Human Factors in Computing Systems - Proceedings

Conference

Conference	2024 CHI Conference on Human Factors in Computing Sytems (CHI 2024)
Country/Territory	United States
City	Honolulu
Period	11/05/24 → 16/05/24
Internet address	https://chi2024.acm.org/for-attendees/

Funding

This research was partially supported by the 2021 CCF-Tencent Rhino-Bird Research Fund, the Research Matching Grant Scheme (RMGS, Project No. 9229095), 2023 Guangzhou Science and Technology Program City-University Joint Funding Project (Project No. 2023A03J0001), Guangdong Provincial Key Lab of Integrated Communication, Sensing and Computation for Ubiquitous Internet of Things (No.2023B1212010007), and Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant. We thank our reviewers for their constructive feedback and participants for their participation.

Research Keywords

collaborative programming
large language model
natural language interface
natural language programming
prompt engineering

Access Output

10.1145/3613904.3642212

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Feng, L., Yen, R., You, Y., Fan, M., Zhao, J., & Lu, Z. (2024). CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming. In CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems Article 934 (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3613904.3642212

@inproceedings{c022a9e78c834d68a693051760f2ce0d,

title = "CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming",

abstract = "Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and context-switching among programmers from varying backgrounds. However, programmers may face challenges during prompt engineering in a collaborative setting as they need to actively keep aware of their collaborators' progress and intents. In this paper, we aim to investigate ways to assist programmers' prompt engineering in a collaborative context. We first conducted a formative study to understand the workflows and challenges of programmers when using NL for collaborative programming. Based on our findings, we implemented a prototype, CoPrompt, to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. Our user study indicates that CoPrompt assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs. {\textcopyright} 2024 Copyright held by the owner/author(s)",

keywords = "collaborative programming, large language model, natural language interface, natural language programming, prompt engineering",

author = "Li Feng and Ryan Yen and Yuzhe You and Mingming Fan and Jian Zhao and Zhicong Lu",

year = "2024",

month = may,

doi = "10.1145/3613904.3642212",

language = "English",

isbn = "9798400703300",

series = "Conference on Human Factors in Computing Systems - Proceedings",

publisher = "Association for Computing Machinery",

booktitle = "CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems",

address = "United States",

note = "2024 CHI Conference on Human Factors in Computing Sytems (CHI 2024) : {"}Surfing the World{"} ; Conference date: 11-05-2024 Through 16-05-2024",

url = "https://chi2024.acm.org/for-attendees/",

}

Feng, L, Yen, R, You, Y, Fan, M, Zhao, J & Lu, Z 2024, CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming. in CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems., 934, Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, 2024 CHI Conference on Human Factors in Computing Sytems (CHI 2024), Honolulu, United States, 11/05/24. https://doi.org/10.1145/3613904.3642212

CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming. / Feng, Li; Yen, Ryan; You, Yuzhe et al.
CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2024. 934 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - CoPrompt

T2 - 2024 CHI Conference on Human Factors in Computing Sytems (CHI 2024)

AU - Feng, Li

AU - Yen, Ryan

AU - You, Yuzhe

AU - Fan, Mingming

AU - Zhao, Jian

AU - Lu, Zhicong

PY - 2024/5

Y1 - 2024/5

N2 - Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and context-switching among programmers from varying backgrounds. However, programmers may face challenges during prompt engineering in a collaborative setting as they need to actively keep aware of their collaborators' progress and intents. In this paper, we aim to investigate ways to assist programmers' prompt engineering in a collaborative context. We first conducted a formative study to understand the workflows and challenges of programmers when using NL for collaborative programming. Based on our findings, we implemented a prototype, CoPrompt, to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. Our user study indicates that CoPrompt assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs. © 2024 Copyright held by the owner/author(s)

AB - Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and context-switching among programmers from varying backgrounds. However, programmers may face challenges during prompt engineering in a collaborative setting as they need to actively keep aware of their collaborators' progress and intents. In this paper, we aim to investigate ways to assist programmers' prompt engineering in a collaborative context. We first conducted a formative study to understand the workflows and challenges of programmers when using NL for collaborative programming. Based on our findings, we implemented a prototype, CoPrompt, to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. Our user study indicates that CoPrompt assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs. © 2024 Copyright held by the owner/author(s)

KW - collaborative programming

KW - large language model

KW - natural language interface

KW - natural language programming

KW - prompt engineering

UR - http://www.scopus.com/inward/record.url?scp=85194868719&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85194868719&origin=recordpage

U2 - 10.1145/3613904.3642212

DO - 10.1145/3613904.3642212

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798400703300

T3 - Conference on Human Factors in Computing Systems - Proceedings

BT - CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

Y2 - 11 May 2024 through 16 May 2024

ER -

Feng L, Yen R, You Y, Fan M, Zhao J, Lu Z. CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming. In CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. 2024. 934. (Conference on Human Factors in Computing Systems - Proceedings). Epub 2024 May 11. doi: 10.1145/3613904.3642212

CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

DON_RMG: A Fan-Centered Virtual Idol Design and Interaction System - RMGS

Cite this

CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

DON_RMG: A Fan-Centered Virtual Idol Design and Interaction System - RMGS

Cite this