Logo do repositório
 
Publicação

Prompt-gaming: a pilot study on LLM-evaluating agent in a meaningful energy game

2024-05-02Comunicação em conferência Acesso aberto
Ver registo simples
datacite.subject.fosCiências Naturais::Ciências da Computação e da Informação
dc.contributor.authorIsaza-Giraldo, Andrés
dc.contributor.authorBala, Paulo
dc.contributor.authorCampos, Pedro F.
dc.contributor.authorPereira, Lucas
dc.contributor.authorBala, Paulo
dc.contributor.authorPereira Campos, Pedro Filipe
dc.contributor.authorPereira, Lucas
dc.date.accessioned2026-07-20T15:13:29Z
dc.date.available2026-07-20T15:13:29Z
dc.date.issued2024-05-02
dc.description.abstractBuilding on previous work on incorporating large language mod els (LLM) in gaming, we investigate the possibility of implement ing LLM as evaluating agents of open-ended challenges in serious games and its potential to facilitate a meaningful experience for the player. We contribute with a sustainability game prototype in a single natural language prompt about energy communities and we tested it with 13 participants inside ChatGPT-3.5. Two partici pants were already aware of energy communities before the game, and eight of the remaining 11 gained valuable knowledge about the specifc topic. Comparing ChatGPT-3.5 evaluations of players’ interaction with an expert’s assessment, ChatGPT-3.5 correctly evaluated 81% of player’s answers. Our results are encouraging and show the potential of using LLMs as mediating agents in ed ucational games, while also allowing easy prototyping of games through natural language prompts.eng
dc.identifier.citationAndrés Isaza-Giraldo, Paulo Bala, Pedro F. Campos, and Lucas Pereira. 2024. Prompt-Gaming: A Pilot Study on LLM-Evaluating Agent in a Meaningful Energy Game. In Extended Abstracts of the CHI Conference on Human Factorsin Computing Systems (CHI EA ’24), May 11–16, 2024
dc.identifier.doi10.1145/3613905.3650774
dc.identifier.isbn979-8-4007-0331-7/24/05
dc.identifier.urihttp://hdl.handle.net/10400.13/7877
dc.language.isoeng
dc.peerreviewedyes
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.ispartofExtended Abstracts of the CHI Conference on Human Factors in Computing Systems
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subjectLarge Language Models (LLMs)
dc.subjectSerious games
dc.subjectGame-based Learning
dc.subjectSustainability
dc.subjectEnergy communities
dc.subjectNatural Language Pro cessing (NLP)
dc.subject.
dc.subjectFaculdade de Ciências Exatas e da Engenharia
dc.titlePrompt-gaming: a pilot study on LLM-evaluating agent in a meaningful energy gameeng
dc.typeconference paper
dspace.entity.typePublication
oaire.citation.conferenceDate2024
oaire.citation.conferencePlaceHonolulu, HI, USA
oaire.citation.titleExtended Abstracts of the CHI Conference on Human Factorsin Computing Systems (CHI EA ’24)
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameBala
person.familyNamePereira Campos
person.familyNamePereira
person.givenNamePaulo
person.givenNamePedro Filipe
person.givenNameLucas
person.identifierIkF3sn4AAAAJ
person.identifier.ciencia-id911F-BB1A-C970
person.identifier.ciencia-id7C19-B5E5-01CA
person.identifier.ciencia-id421F-7B0E-8647
person.identifier.orcid0000-0003-1743-0261
person.identifier.orcid0000-0001-7706-5038
person.identifier.orcid0000-0002-9110-8775
person.identifier.ridH-4480-2014
person.identifier.scopus-author-id8909782300
relation.isAuthorOfPublication0dad3d7f-3c49-4c26-9dea-5fdb1deff6e6
relation.isAuthorOfPublicationfb4a962b-b799-4ba2-8778-3d9d0a64b2b0
relation.isAuthorOfPublicationeae43ee1-ef29-4bb3-afd4-876b1ef849a0
relation.isAuthorOfPublication.latestForDiscovery0dad3d7f-3c49-4c26-9dea-5fdb1deff6e6

Ficheiros

Coleções

Publicações em Atas de Congressos/Conferências, etc.