Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Cosme, D., Galvão, A. & Brito e Abreu, F. (2026). A Systematic Literature Review on LLM-Based Content Classification. In Jorge Bernardino · Ana Fred · Antonella Poggi · Le Gruenwald · Frans Coenen · Elio Masciari · David Aveiro (Ed.), Knowledge Discovery, Knowledge Engineering and Knowledge Management. (pp. 121-149). Cham: Springer.
Exportar Referência (IEEE) 
D. F. Cosme et al.,  "A Systematic Literature Review on LLM-Based Content Classification", in Knowledge Discovery, Knowledge Engineering and Knowledge Management, Jorge Bernardino · Ana Fred · Antonella Poggi · Le Gruenwald · Frans Coenen · Elio Masciari · David Aveiro, Ed., Cham, Springer, 2026, vol. 2703, pp. 121-149
Exportar BibTeX 
@incollection{cosme2026_1764928308786,
	author = "Cosme, D. and Galvão, A. and Brito e Abreu, F.",
	title = "A Systematic Literature Review on LLM-Based Content Classification",
	chapter = "",
	booktitle = "Knowledge Discovery, Knowledge Engineering and Knowledge Management",
	year = "2026",
	volume = "2703",
	series = "Communications in Computer and Information Science",
	edition = "1",
	pages = "121-121",
	publisher = "Springer",
	address = "Cham",
	url = "https://doi.org/10.1007/978-3-032-06878-1_7"
}
Exportar RIS 
TY  - CHAP
TI  - A Systematic Literature Review on LLM-Based Content Classification
T2  - Knowledge Discovery, Knowledge Engineering and Knowledge Management
VL  - 2703
AU  - Cosme, D.
AU  - Galvão, A.
AU  - Brito e Abreu, F.
PY  - 2026
SP  - 121-149
SN  - 1865-0929
DO  - 10.1007/978-3-032-06878-1_7
CY  - Cham
UR  - https://doi.org/10.1007/978-3-032-06878-1_7
AB  - This review examines how LLMs, particularly those using transformer architectures, have addressed persistent challenges in text classification through their advanced context understanding and generative capabilities. Despite significant progress, the review highlights gaps in current research, such as the need for greater transparency, reduced computational cost, and better management of model hallucinations. The paper concludes with recommendations for future research to improve the use of LLMs in content classification and ensure their effective use in various domains.
ER  -