Multimodal Large Language Models as Built Environment Auditing Tools

Simple item page
dc.contributor.authorJang, Kee Moonen
dc.contributor.authorKim, Junghwanen
dc.date.accessioned2024-12-03T14:04:28Zen
dc.date.available2024-12-03T14:04:28Zen
dc.date.issued2024-10-07en
dc.description.abstractThis research showcases the transformative potential of large language models (LLMs) for built environment auditing from street-view images. By empirically testing the performances of two multimodal LLMs, ChatGPT and Gemini, we confirmed that LLM-based audits strongly agree with virtual audits processed by a conventional deep learning-based method (DeepLabv3+), which has been widely adopted by existing studies on urban visual analytics. Unlike conventional field or virtual audits that require labor-intensive manual inspection or technical expertise to run computer vision algorithms, our results show that LLMs can offer an intuitive tool despite the user’s level of technical proficiency. This would allow a broader range of policy and planning stakeholders to employ LLM-based built environment auditing instruments for smart urban infrastructure management.en
dc.description.sponsorshipJunghwan Kim was supported by the Institute for Society, Culture and Environment (ISCE) at Virginia Tech and by 4-VA, a collaborative partnership for advancing the Commonwealth of Virginia.en
dc.description.versionAccepted versionen
dc.format.extent7 page(s)en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1080/00330124.2024.2404894en
dc.identifier.eissn1467-9272en
dc.identifier.issn0033-0124en
dc.identifier.orcidKim, Junghwan [0000-0002-7275-769X]en
dc.identifier.urihttps://hdl.handle.net/10919/123715en
dc.language.isoenen
dc.publisherRoutledgeen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectauditen
dc.subjectbuilt environmenten
dc.subjectChatGPTen
dc.subjectGeminien
dc.subjectstreet-view imagesen
dc.titleMultimodal Large Language Models as Built Environment Auditing Toolsen
dc.title.serialThe Professional Geographeren
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherArticleen
pubs.organisational-groupVirginia Techen
pubs.organisational-groupVirginia Tech/Natural Resources & Environmenten
pubs.organisational-groupVirginia Tech/Natural Resources & Environment/Geographyen
pubs.organisational-groupVirginia Tech/Natural Resources & Environment/Geography/Geography T&R facultyen
pubs.organisational-groupVirginia Tech/All T&R Facultyen
pubs.organisational-groupVirginia Tech/Natural Resources & Environment/CNRE T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Jang_and_Kim_MultimodalLargeLanguageModelsasBuiltEnvironmentAuditingTools.pdf
Size:
2.32 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
1.5 KB
Format:
Plain Text
Description:
Download

Collections

All Faculty Deposits
Scholarly Works, Geography