Repository logo
 
Publication

Prompting for socially intelligent agents with chatGPT

2023Conference object Open access
Simple item page
dc.contributor.authorAntunes, Ana
dc.contributor.authorCampos, Joana
dc.contributor.authorGuimarães, Manuel
dc.contributor.authorDias, João
dc.contributor.authorSantos, Pedro A.
dc.date.accessioned2024-03-13T10:13:30Z
dc.date.available2024-03-13T10:13:30Z
dc.date.issued2023
dc.description.abstractSocially Intelligent Agents (SIAs) have become increasingly popular in various contexts, including education and entertainment. However, creating complex social scenarios tailored to a designer's specific goals remains a significant challenge. The authoring burden can be substantial, limiting the potential of SIAs to deliver rich, engaging experiences. In this work, we propose leveraging the extensive knowledge stored within Large Language Models and use theory-driven prompting to extract social practices and identify appropriate social affordances for a scenario description. Our prompting approach aims to guide the system into considering the essential components (beliefs and desires) necessary to produce intentions, actions, and emotions(1). Results show that our approach produces large amounts of accurate and new information that can add value to the scenario. However, the process can introduce inaccuracies without human supervision.pt_PT
dc.description.sponsorshipPhD grant 2021/06419/BD;pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1145/3570945.3607303pt_PT
dc.identifier.isbn978-1-4503-9994-4
dc.identifier.urihttp://hdl.handle.net/10400.1/20496
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherAssociation for Computing Machinerypt_PT
dc.relationInstituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa
dc.relationAlgarve Centre for Marine Sciences
dc.relationCentre for Marine and Environmental Research
dc.relationAlgarve Centre for Marine Sciences
dc.relationSocial Learning for Intelligent Characters
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectSocially iIntelligent agentspt_PT
dc.subjectAuthoring social scenariospt_PT
dc.subjectPrompt engineeringpt_PT
dc.subjectLarge language modelspt_PT
dc.titlePrompting for socially intelligent agents with chatGPTpt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.awardTitleInstituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa
oaire.awardTitleAlgarve Centre for Marine Sciences
oaire.awardTitleCentre for Marine and Environmental Research
oaire.awardTitleAlgarve Centre for Marine Sciences
oaire.awardTitleSocial Learning for Intelligent Characters
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50021%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04326%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/LA%2FP%2F0101%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F04326%2F2020/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/Concurso para Financiamento de Projetos de Investigação Científica e Desenvolvimento Tecnológico em Todos os Domínios Científicos - 2017/PTDC%2FCCI-COM%2F30787%2F2017/PT
oaire.citation.endPage9pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleIVA '23: Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agentspt_PT
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStream6817 - DCRRNI ID
oaire.fundingStreamConcurso para Financiamento de Projetos de Investigação Científica e Desenvolvimento Tecnológico em Todos os Domínios Científicos - 2017
person.familyNameDias
person.givenNameJoão
person.identifier.ciencia-id541C-36A9-F1A0
person.identifier.orcid0000-0002-1653-1821
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublication66c729e3-99f2-4ddc-8da4-7c66e590800b
relation.isAuthorOfPublication.latestForDiscovery66c729e3-99f2-4ddc-8da4-7c66e590800b
relation.isProjectOfPublication0b14d63a-8f78-4e31-8a86-b72e1f07871f
relation.isProjectOfPublicationfafa76a6-2cd2-4a6d-a3c9-772f34d3b91f
relation.isProjectOfPublication794d4c77-c731-471e-bc96-5a41dcd3d872
relation.isProjectOfPublication15f91d45-e070-47d8-b6b8-efd4de31d9a8
relation.isProjectOfPublication236463b2-7173-42db-a836-b76bd481336a
relation.isProjectOfPublication.latestForDiscovery794d4c77-c731-471e-bc96-5a41dcd3d872

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
3570945.3607303.pdf
Size:
789.98 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.46 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)
CCM2-Artigos (em revistas ou actas indexadas)