Utilize este identificador para referenciar este registo: http://hdl.handle.net/10071/34581
Autoria: Cosme, D.
Galvão, A.
Brito e Abreu, F.
Editor: Frans Coenen
Ana Fred
Jorge Bernardino
Data: 2024
Título próprio: A systematic literature review on LLM-based information retrieval: The issue of contents classification
Título e volume do livro: Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management
Paginação: 135 - 146
Título do evento: 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (KDIR2024)
Referência bibliográfica: Cosme, D., Galvão, A., & Brito e Abreu, F. (2024). A systematic literature review on LLM-based information retrieval: The issue of contents classification. In F. Coenen, A. Fred, & J. Bernardino (Eds.), Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (pp. 135-146). SciTePress. https://doi.org/10.5220/0013062300003838
ISSN: 2184-3228
ISBN: 978-989-758-716-0
DOI (Digital Object Identifier): 10.5220/0013062300003838
Palavras-chave: Systematic Literature Review
Large Language Model
Information Retrieval
Contents Classification
Resumo: This paper conducts a systematic literature review on applying Large Language Models (LLMs) in information retrieval, specifically focusing on content classification. The review explores how LLMs, particularly those based on transformer architectures, have addressed long-standing challenges in text classification by leveraging their advanced context understanding and generative capabilities. Despite the rapid advancements, the review identifies gaps in current research, such as the need for improved transparency, reduced computational costs, and the handling of model hallucinations. The paper concludes with recommendations for future research directions to optimize the use of LLMs in content classification, ensuring their effective deployment across various domains.
Arbitragem científica: yes
Acesso: Acesso Aberto
Aparece nas coleções:ISTAR-CRI - Comunicações a conferências internacionais

Ficheiros deste registo:
Ficheiro TamanhoFormato 
conferenceObject_106644.pdf376,87 kBAdobe PDFVer/Abrir


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis Logotipo do Orcid 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.