VICTOR VECTORS @ DIPROMATS 2024: Propaganda Detection with LLM Paraphrasing and Machine Translation

Simple item page
dc.catalogadordfo
dc.contributor.authorFernández, Miguel
dc.contributor.authorOjeda Aguila, Maximiliano Eduardo
dc.contributor.authorGuevara, Lilly
dc.contributor.authorVarela, Diego
dc.contributor.authorMendoza Rocha, Marcelo Gabriel
dc.contributor.authorBarrón-Cedeno, Alberto
dc.date.accessioned2025-05-22T16:42:36Z
dc.date.available2025-05-22T16:42:36Z
dc.date.issued2024
dc.description.abstractIdentifying propaganda in social media posts is an important task that can help to better understand the strategies applied by policy makers and stake holders when trying to convey their message to the general public. We describe our participation in DIPROMATS 2024 Task 1 on the automated detection and characterization of propaganda techniques and narratives from diplomats of major powers. We show an efficient way to utilize Large Language Models (LLMs) to paraphrase a sample of the training instances, to balance the class distribution in the datasets provided by the shared task. Our submission ranked 1st in Subtask-1a in English (ICM score of 0.2123) and 1st in the bilingual evaluation (ICM score of 0.2048). We also achieved top-3 rankings in Spanish and subtasks 1b and 1c.
dc.description.funderNational Center for Artificial Intelligence
dc.description.funderCENIA
dc.description.funderIMFD ANID
dc.description.funderANID Fondecyt
dc.fechaingreso.objetodigital2025-05-22
dc.fuente.origenSCOPUS
dc.identifier.issn16130073
dc.identifier.scopusidSCOPUS_ID:85204375548
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/104446
dc.information.autorucEscuela de Ingeniería; Ojeda Aguila Maximiliano Eduardo; S/I; 1246333
dc.information.autorucEscuela de Ingeniería; Mendoza Rocha Marcelo Gabriel; S/I; 1237020
dc.language.isoen
dc.nota.accesocontenido completo
dc.publisherCEUR-WS
dc.relation.ispartofIberian Languages Evaluation Forum (2024)
dc.revistaCEUR Workshop Proceedings
dc.rightsacceso abierto
dc.rights.licenseAtribución/Reconocimiento 4.0 Internacional
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/deed.es
dc.subjectData augmentation
dc.subjectLLMs
dc.subjectParaphrasing
dc.subjectPropaganda detection
dc.subjectUnbalanced data
dc.subject.ddc000
dc.subject.deweyCiencias de la computaciónes_ES
dc.titleVICTOR VECTORS @ DIPROMATS 2024: Propaganda Detection with LLM Paraphrasing and Machine Translation
dc.typecomunicación de congreso
dc.volumen3756
sipa.codpersvinculados1246333
sipa.codpersvinculados1237020
sipa.trazabilidadSCOPUS;2024-09-29
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
DIPROMATS2024_paper8.pdf
Size:
1.7 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de conferencia