Powered by OpenAIRE graph
Found an issue? Give us feedback
ZENODOarrow_drop_down
ZENODO
Dataset . 2025
License: CC BY
Data sources: Datacite
ZENODO
Dataset . 2025
License: CC BY
Data sources: Datacite
versions View all 2 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

STAR-Prompting: Sistema Estruturado de Prompts através do método STAR aplicados para a Defesa e Segurança

Authors: Gonçalves, Clendson; Lopes de Mendonca, Fabio Lucio; Canedo, Edna Dias; Albuquerque, Robson; Amvame Nze, Georges Daniel; Alves da Silva, Daniel;

STAR-Prompting: Sistema Estruturado de Prompts através do método STAR aplicados para a Defesa e Segurança

Abstract

O método STAR (Situação, Tarefa, Ação, Resultado) é originalmente usado na área de recursos humanos e oferece uma estrutura lógica para respostas em entrevistas comportamentais. Este estudo propõe o STAR-Prompting, uma técnica de engenharia de prompt baseada na lógica do método STAR, para interações com modelos de linguagem de grande escala (LLM), visando respostas mais confiáveis, especialmente em contextos de Defesa e Segurança. Os resultados comparam prompts em linguagem livre e prompts estruturados com o sistema proposto em quatro LLMs: Gemini Flash 2.0, Llama 3.3 70B, GPT-4o-mini e Claude 3.5 Sonnet. A análise mostra que o uso do STAR-Prompting melhora a qualidade das respostas e destaca seu potencial promissor para aprimorar a comunicação entre humanos e sistemas de IA, reduzindo a ocorrência de ambiguidades e elevando a qualidade das respostas geradas.

Related Organizations
Keywords

Engenharia de Prompt, Defesa e Segurança, Comunicação Humano-IA, Método STAR, Inteligência Artificial Conversacional

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average