Weakly supervised veracity classification with LLM-predicted credibility signals

Abstract Credibility signals represent a wide range of heuristics typically used by journalists and fact-checkers to assess the veracity of online content. Automating the extraction of credibility signals presents significant challenges due to the necessity of training high-accuracy, signal-specific...

Descrición completa

Detalles Bibliográficos

Principais autores:	João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton
Formato:	Artigo
Idioma:	Inglês
Publicado:	SpringerOpen 2025-02-01
Series:	EPJ Data Science
Assuntos:	Veracity classification Large language models Weak supervision Credibility signals
Acceso en liña:	https://doi.org/10.1140/epjds/s13688-025-00534-0
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!