RT Conference Proceedings
T1 I2C-Huelva at SemEval-2024 Task 8: Boosting AI-Generated Text Detection with Multimodal Models and Optimized Ensembles
A1 Rodero Peña, Alberto
A1 Mata Vázquez, Jacinto
A1 Pachón Álvarez, Victoria
AB With the rise of AI-based text generators, the need for effective detection mechanisms has become paramount. This paper presents new techniques for building adaptable models and optimizing training aspects for identifying synthetically produced texts across multiple generators and domains. The study, divided into binary and multilabel classification tasks, avoids overfitting through strategic training data limitation. A key innovation is the incorporation of multimodal models that blend numerical text features with conventional NLP approaches. The work also delves into optimizing ensemble model combinations via various voting methods, focusing on accuracy as the official metric. The optimized ensemble strategy demonstrates significant efficacy in both subtasks, highlighting the potential of multimodal and ensemble methods in enhancing the robustness of detection systems against emerging text generators.
PB Association for Computational Linguistics
YR 2024
FD 2024-06
LK https://hdl.handle.net/10272/24395
UL https://hdl.handle.net/10272/24395
LA eng
NO Rodero Peña, A., Mata Vazquez, J., & Pachón Álvarez, V. (2024). I2C-Huelva at SemEval-2024 Task 8: Boosting AI-Generated Text Detection with Multimodal Models and Optimized Ensembles. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024) (pp. 845–852). Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.semeval-1.121
DS Repositorio Institucional de la Universidad de Huelva
RD 15 jul 2026