English

BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning

Computation and Language 2025-09-01 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2508.21294,
  title  = {BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning},
  author = {João Guilherme Alves Santos and Giovana Kerche Bonás and Thales Sales Almeida},
  journal= {arXiv preprint arXiv:2508.21294},
  year   = {2025}
}

Comments

12 pages, 5 figures, 2 tables

R2 v1 2026-07-01T05:11:25.245Z