Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Himmi, Anas, Staerman, Guillaume, Picot, Marine, Colombo, Pierre, Guerreiro, Nuno M.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911781160484864
author Himmi, Anas
Staerman, Guillaume
Picot, Marine
Colombo, Pierre
Guerreiro, Nuno M.
author_facet Himmi, Anas
Staerman, Guillaume
Picot, Marine
Colombo, Pierre
Guerreiro, Nuno M.
contents Hallucinated translations pose significant threats and safety concerns when it comes to the practical deployment of machine translation systems. Previous research works have identified that detectors exhibit complementary performance different detectors excel at detecting different types of hallucinations. In this paper, we propose to address the limitations of individual detectors by combining them and introducing a straightforward method for aggregating multiple detectors. Our results demonstrate the efficacy of our aggregated detector, providing a promising step towards evermore reliable machine translation systems.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation
Himmi, Anas
Staerman, Guillaume
Picot, Marine
Colombo, Pierre
Guerreiro, Nuno M.
Computation and Language
Hallucinated translations pose significant threats and safety concerns when it comes to the practical deployment of machine translation systems. Previous research works have identified that detectors exhibit complementary performance different detectors excel at detecting different types of hallucinations. In this paper, we propose to address the limitations of individual detectors by combining them and introducing a straightforward method for aggregating multiple detectors. Our results demonstrate the efficacy of our aggregated detector, providing a promising step towards evermore reliable machine translation systems.
title Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation
topic Computation and Language
url https://arxiv.org/abs/2402.13331