BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning

• URL: http://arxiv.org/abs/2508.21294v1
• Date: Fri, 29 Aug 2025 01:23:28 GMT
• Title: BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning
• Abstract summary: 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.<n> Captioning strategies increase accessibility to text-only models by more than 40%, producing 1,422 usable questions.
• Score: 3.364554138758565
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams [5.232617124162657]
  We introduce BLUEX v2, a benchmark derived from the second-phase entrance exams of Brazil's two leading universities.<n>Our dataset comprises 395 questions unfolding into 919 graded subquestions, with 55.7% of questions containing associated images.<n>Results reveal a 4.92-point performance spread across models, with Mathematical Reasoning and Image Understanding emerging as the hardest capability dimensions.
  arXiv  Detail & Related papers  (2026-06-21T23:45:49Z)
• Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective [40.29094043868067]
  We present the first systematic study of the diffusion language embedding model, which outperforms the LLM-based embedding model by 20% on long-document retrieval.<n>Our analysis verifies that bidirectional attention is crucial for encoding global context in long and complex text.
  arXiv  Detail & Related papers  (2025-05-21T02:59:14Z)
• Large Language Model-guided Document Selection [23.673690115025913]
  Large Language Model (LLM) pre-training exhausts an ever growing compute budget. Recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. We explore a promising direction for scalable general-domain document selection.
  arXiv  Detail & Related papers  (2024-06-07T04:52:46Z)
• CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models [53.9835961434552]
  We introduce the Chinese Instruction-Following Benchmark (CIF-Bench) to evaluate the generalizability of large language models (LLMs) to the Chinese language. CIF-Bench comprises 150 tasks and 15,000 input-output pairs, developed by native speakers to test complex reasoning and Chinese cultural nuances. To mitigate data contamination, we release only half of the dataset publicly, with the remainder kept private, and introduce diversified instructions to minimize score variance.
  arXiv  Detail & Related papers  (2024-02-20T16:02:12Z)
• Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning [58.92843729869586]
  Vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, but their mastery in a few languages like English restricts their applicability in broader communities. We propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF) We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance.
  arXiv  Detail & Related papers  (2024-01-30T17:14:05Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• MLLMs-Augmented Visual-Language Representation Learning [70.5293060238008]
  We demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. We propose "text shearing" to maintain the quality and availability of extended captions.
  arXiv  Detail & Related papers  (2023-11-30T18:05:52Z)
• CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages [86.90220551111096]
  Training datasets for large language models (LLMs) are often not fully disclosed. We present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages.
  arXiv  Detail & Related papers  (2023-09-17T23:49:10Z)
• Contextual Biasing of Named-Entities with Large Language Models [12.396054621526643]
  This paper studies contextual biasing with Large Language Models (LLMs) During second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to leverage prompts for a LLM without fine tuning during rescoring which incorporate a biasing list and few-shot examples.
  arXiv  Detail & Related papers  (2023-09-01T20:15:48Z)
• BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions [41.825273034537204]
  Vision Language Models (VLMs) cannot accurately interpret images infused with text. The present study introduces BLIVA: an augmented version of InstructBLIP with Visual Assistant. Our model significantly enhances performance in processing text-rich VQA benchmarks and in undertaking general (not particularly text-rich) VQA benchmarks.
  arXiv  Detail & Related papers  (2023-08-19T07:53:43Z)
• L-Eval: Instituting Standardized Evaluation for Long Context Language Models [91.05820785008527]
  We propose L-Eval to institute a more standardized evaluation for long context language models (LCLMs) We build a new evaluation suite containing 20 sub-tasks, 508 long documents, and over 2,000 human-labeled query-response pairs. Results show that popular n-gram matching metrics generally can not correlate well with human judgment.
  arXiv  Detail & Related papers  (2023-07-20T17:59:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.