BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Santos, João Guilherme Alves, Bonás, Giovana Kerche, Almeida, Thales Sales
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915470120058880
author Santos, João Guilherme Alves
Bonás, Giovana Kerche
Almeida, Thales Sales
author_facet Santos, João Guilherme Alves
Bonás, Giovana Kerche
Almeida, Thales Sales
contents With the growing capabilities of Large Language Models (LLMs), there is an increasing need for robust evaluation methods, especially in multilingual and non-English contexts. We present an updated version of the BLUEX dataset, now including 2024-2025 exams and automatically generated image captions using state-of-the-art models, enhancing its relevance for data contamination studies in LLM pretraining. Captioning strategies increase accessibility to text-only models by more than 40%, producing 1,422 usable questions, more than doubling the number in the original BLUEX. We evaluated commercial and open-source LLMs and their ability to leverage visual context through captions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21294
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning
Santos, João Guilherme Alves
Bonás, Giovana Kerche
Almeida, Thales Sales
Computation and Language
Artificial Intelligence
With the growing capabilities of Large Language Models (LLMs), there is an increasing need for robust evaluation methods, especially in multilingual and non-English contexts. We present an updated version of the BLUEX dataset, now including 2024-2025 exams and automatically generated image captions using state-of-the-art models, enhancing its relevance for data contamination studies in LLM pretraining. Captioning strategies increase accessibility to text-only models by more than 40%, producing 1,422 usable questions, more than doubling the number in the original BLUEX. We evaluated commercial and open-source LLMs and their ability to leverage visual context through captions.
title BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.21294