Are Large Language Models Moral Hypocrites? A Study Based on MoralFoundations

Página do item simplificado
dc.contributor.authorJosé Luiz Nunes
dc.contributor.authorGUILHERME DA FRANCA COUTO FERNANDES DE ALMEIDA
dc.contributor.authorAraujo, Marcelo de
dc.contributor.authorBarbosa, Simone D. J.
dc.creatorJosé Luiz Nunes
dc.creatorAraujo, Marcelo de
dc.creatorBarbosa, Simone D. J.
dc.date.accessioned2025-02-12T22:37:10Z
dc.date.available2025-02-12T22:37:10Z
dc.date.issued2021
dc.description.abstractLarge language models (LLMs) have taken centre stage indebates on Artificial Intelligence. Yet there remains a gap inhow to assess LLMs’ conformity to important human values.In this paper, we investigate whether state-of-the-art LLMs,GPT-4 and Claude 2.1 (Gemini Pro and LLAMA 2 did notgenerate valid results) are moral hypocrites. We employ tworesearch instruments based on the Moral Foundations The-ory: (i) the Moral Foundations Questionnaire (MFQ), whichinvestigates which values are considered morally relevant inabstract moral judgements; and (ii) the Moral FoundationsVignettes (MFVs), which evaluate moral cognition in con-crete scenarios related to each moral foundation. We charac-terise conflicts in values between these different abstractionsof moral evaluation as hypocrisy. We found that both mod-els displayed reasonable consistency within each instrumentcompared to humans, but they displayed contradictory andhypocritical behaviour when we compared the abstract val-ues present in the MFQ to the evaluation of concrete moralviolations of the MFV.en
dc.formatDigital
dc.format.extentp. 1074 - 1087
dc.identifier.urihttps://repositorio.insper.edu.br/handle/11224/7380
dc.language.isoInglês
dc.publisherThe AAAI Press
dc.titleAre Large Language Models Moral Hypocrites? A Study Based on MoralFoundations
dc.typeconference paper
dspace.entity.typePublication
local.description.eventProceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES2024)1074
local.identifier.sourceUrihttps://ojs.aaai.org/index.php/AIES/issue/view/609
local.publisher.cityNew York
local.publisher.countryEstados Unidos
local.subject.cnpqCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
local.subject.cnpqCIENCIAS HUMANAS::FILOSOFIA::ETICA
local.subject.cnpqCIENCIAS HUMANAS::PSICOLOGIA
local.subject.cnpqCIENCIAS HUMANAS::FILOSOFIA
local.typeTrabalho de Evento
relation.isAuthorOfPublication8575f912-24df-44e3-8512-a288b848e951
relation.isAuthorOfPublication.latestForDiscovery8575f912-24df-44e3-8512-a288b848e951
Arquivos
Pacote Original
Agora exibindo 1 - 2 de 2
N/D
Nome:
Primeira_Pagina_Trabalho_de_Evento_2024_Are_large_language_models_moral_Hypocrites_a_study_based_on_moral_foundations_TC.pdf
Tamanho:
45.55 KB
Formato:
Adobe Portable Document Format
Baixar
N/D
Nome:
ACESSO_RESTRITO_Trabalho_de_Evento_2024_Are_large_language_models_moral_Hypocrites_a_study_based_on_moral_foundations_TC.pdf
Tamanho:
210.69 KB
Formato:
Adobe Portable Document Format
Baixar
Licença do Pacote
Agora exibindo 1 - 1 de 1
N/D
Nome:
license.txt
Tamanho:
236 B
Formato:
Item-specific license agreed upon to submission
Descrição:
Baixar
Coleções
Coleção de Trabalhos Apresentados em Eventos