PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding

• URL: http://arxiv.org/abs/2608.21853v1
• Date: Sat, 22 Aug 2026 08:55:56 GMT
• Title: PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding
• Abstract summary: PUMA is a benchmark of 900 hand-crafted tasks designed to probe the limits of multimodal models in the Polish cultural and linguistic context.<n>The dataset evaluates both cultural understanding and practical skill in processing text, images, audio, and visually rich documents.
• Score: 0.01666714735110092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are increasingly moving beyond text processing, adding support for other modalities such as images and audio. While text understanding and generation have been extensively studied, multimodal data processing capabilities, particularly in the context of cultures and languages other than English, have not yet been evaluated comprehensively. In this paper, we propose PUMA (Polish Unified Multimodal Assessment), a novel benchmark of 900 hand-crafted tasks designed to probe the limits of multimodal models in the Polish cultural and linguistic context. The dataset evaluates both cultural understanding and practical skill in processing text, images, audio, and visually rich documents. Our extensive evaluation of frontier commercial models, open-weights models, and specialized smaller systems highlights a significant performance gap. While top commercial models achieve high scores in visual question answering, most models struggle with complex audio or document understanding. We open-source our evaluation framework to advance localized multimodal AI research.

Related papers

• Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework [38.98519875112922]
  Vision-language models (VLMs) are trained on English-centric data, limiting their performance in other languages and cultural contexts.<n>We reproduce and adapt the LLaVA-Next methodology to create a set of Polish VLMs.<n>We observe a +9.5% improvement over LLaVA-1.6-una-13B on a Polish-adapted MMBench, along with higher-quality captions in generative evaluations.
  arXiv  Detail & Related papers  (2026-02-15T09:54:40Z)
• Multimodal Evaluation of Russian-language Architectures [88.00147763684451]
  We introduce Mera Multi, an open multimodal evaluation framework for Russian-spoken architectures.<n>The benchmark is instruction-based and encompasses default text, image, audio, and video modalities.<n>Mera Multi provides a replicable methodology for constructing multimodal benchmarks in typologically diverse languages.
  arXiv  Detail & Related papers  (2025-11-19T15:43:53Z)
• TowerVision: Understanding and Improving Multilinguality in Vision-Language Models [56.775118098058506]
  TowerVision is a family of open multilingual vision-language models for both image-text and video-text tasks.<n>By incorporating visual and cultural context during fine-tuning, our models surpass existing approaches.<n>To support further research, we publicly release all models, data, and training recipes.
  arXiv  Detail & Related papers  (2025-10-22T17:02:48Z)
• DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture [14.681676046750342]
  DRISHTIKON is a first-of-its-kind multimodal and multilingual benchmark centered exclusively on Indian culture.<n>The dataset captures rich cultural themes including festivals, attire, cuisines, art forms, and historical heritage.<n>We evaluate a wide range of vision-language models (VLMs), including open-source small and large models, proprietary systems, reasoning-specialized VLMs, and Indic-focused models.
  arXiv  Detail & Related papers  (2025-09-23T17:40:43Z)
• TRINS: Towards Multimodal Language Models that Can Read [61.17806538631744]
  TRINS is a Text-Rich image INStruction dataset. It contains 39,153 text-rich images, captions, and 102,437 questions. We introduce a Language-vision Reading Assistant (LaRA) which is good at understanding textual content within images.
  arXiv  Detail & Related papers  (2024-06-10T18:52:37Z)
• Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
  We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references. Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
  arXiv  Detail & Related papers  (2024-03-05T13:45:46Z)
• The Revolution of Multimodal Large Language Models: A Survey [46.84953515670248]
  Multimodal Large Language Models (MLLMs) can seamlessly integrate visual and textual modalities. This paper provides a review of recent visual-based MLLMs, analyzing their architectural choices, multimodal alignment strategies, and training techniques.
  arXiv  Detail & Related papers  (2024-02-19T19:01:01Z)
• Multimodal Large Language Models: A Survey [36.06016060015404]
  Multimodal language models integrate multiple data types, such as images, text, language, audio, and other heterogeneity. This paper begins by defining the concept of multimodal and examining the historical development of multimodal algorithms. A practical guide is provided, offering insights into the technical aspects of multimodal models. Lastly, we explore the applications of multimodal models and discuss the challenges associated with their development.
  arXiv  Detail & Related papers  (2023-11-22T05:15:12Z)
• TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild [102.93338424976959]
  We introduce TextBind, an almost annotation-free framework for empowering larger language models with the multi-turn interleaved instruction-following capabilities. Our approach requires only image-caption pairs and generates multi-turn multimodal instruction-response conversations from a language model. To accommodate interleaved image-text inputs and outputs, we devise MIM, a language model-centric architecture that seamlessly integrates image encoder and decoder models.
  arXiv  Detail & Related papers  (2023-09-14T15:34:01Z)
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models [122.27878464009181]
  We conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available.
  arXiv  Detail & Related papers  (2023-05-13T11:28:37Z)

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.