https://poloclub.github.io/wordflow!

\n","updatedAt":"2024-01-31T16:49:31.910Z","author":{"_id":"6133f0e6488458a484dee6c1","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1630793941366-noauth.png","fullname":"Jay Wang","name":"xiaohk","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":10,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.47857218980789185},"editors":["xiaohk"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1630793941366-noauth.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2401.14447","authors":[{"_id":"65ba7a0b3e109e7259589c33","name":"Zijie J. Wang","hidden":false},{"_id":"65ba7a0b3e109e7259589c34","name":"Aishwarya Chakravarthy","hidden":false},{"_id":"65ba7a0b3e109e7259589c35","user":{"_id":"635823c40e4fef219825a4e9","avatarUrl":"/avatars/854bb50009baf0e1d6c48c91a88de5e3.svg","isPro":false,"fullname":"David Munechika","user":"davidmunechika","type":"user"},"name":"David Munechika","status":"claimed_verified","statusLastChangedAt":"2024-03-25T09:44:40.923Z","hidden":false},{"_id":"65ba7a0b3e109e7259589c36","user":{"_id":"6321e4f915b7beab57c41160","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1663166024037-6321e4f915b7beab57c41160.jpeg","isPro":false,"fullname":"Duen Horng Chau","user":"polochau","type":"user"},"name":"Duen Horng Chau","status":"claimed_verified","statusLastChangedAt":"2024-08-09T22:58:12.596Z","hidden":false}],"publishedAt":"2024-01-25T18:58:11.000Z","title":"Wordflow: Social Prompt Engineering for Large Language Models","summary":"Large language models (LLMs) require well-crafted prompts for effective use.\nPrompt engineering, the process of designing prompts, is challenging,\nparticularly for non-experts who are less familiar with AI technologies. While\nresearchers have proposed techniques and tools to assist LLM users in prompt\ndesign, these works primarily target AI application developers rather than\nnon-experts. To address this research gap, we propose social prompt\nengineering, a novel paradigm that leverages social computing techniques to\nfacilitate collaborative prompt design. To investigate social prompt\nengineering, we introduce Wordflow, an open-source and social text editor that\nenables everyday users to easily create, run, share, and discover LLM prompts.\nAdditionally, by leveraging modern web technologies, Wordflow allows users to\nrun LLMs locally and privately in their browsers. Two usage scenarios highlight\nhow social prompt engineering and our tool can enhance laypeople's interaction\nwith LLMs. Wordflow is publicly accessible at\nhttps://poloclub.github.io/wordflow.","upvotes":0,"discussionId":"65ba7a0b3e109e7259589c5c","ai_summary":"Social prompt engineering, facilitated by Wordflow, simplifies collaborative prompt design for non-expert users to interact with LLMs more effectively and privately.","ai_keywords":["large language models","prompt engineering","social prompt engineering","Wordflow","social computing","text editor","LLM prompts","web technologies","local execution","private browsing"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["*"]}">

arxiv:2401.14447

Wordflow: Social Prompt Engineering for Large Language Models

Published on Jan 25, 2024

Upvote

Authors:

David Munechika ,

Duen Horng Chau

Abstract

Social prompt engineering, facilitated by Wordflow, simplifies collaborative prompt design for non-expert users to interact with LLMs more effectively and privately.

AI-generated summary

Large language models (LLMs) require well-crafted prompts for effective use. Prompt engineering, the process of designing prompts, is challenging, particularly for non-experts who are less familiar with AI technologies. While researchers have proposed techniques and tools to assist LLM users in prompt design, these works primarily target AI application developers rather than non-experts. To address this research gap, we propose social prompt engineering, a novel paradigm that leverages social computing techniques to facilitate collaborative prompt design. To investigate social prompt engineering, we introduce Wordflow, an open-source and social text editor that enables everyday users to easily create, run, share, and discover LLM prompts. Additionally, by leveraging modern web technologies, Wordflow allows users to run LLMs locally and privately in their browsers. Two usage scenarios highlight how social prompt engineering and our tool can enhance laypeople's interaction with LLMs. Wordflow is publicly accessible at https://poloclub.github.io/wordflow.