Elamur Research⌕
☰
home / papers / 2025 / Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset

Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset

Paper · 2025 · Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki et al.

Summary

Large vision-language models (LVLMs) tend to reflect Western viewpoints. Existing cultural VQA resources often rely on translated material, cover few images or topics, ask shallow factual questions, and treat a culture as uniform. The authors built Pearl to address these gaps. It is a large Arabic multimodal instruction dataset and benchmark focused on cultural heritage, meaning long-standing traditions and practices confirmed by native speakers.

The data was produced by combining agentic LLM/LVLM workflows with repeated rounds of human review, carried out by 37 annotators representing many Arab countries. It covers ten cultural domains and every Arab country, and its question categories target reasoning (hypothesis formation, comparison, chronology) rather than simple recall. The release includes two evaluation benchmarks, Pearl and Pearl-Lite, plus Pearl-X, a subset that probes how one shared concept looks different from country to country.

In tests of open and proprietary LVLMs, models aligned for explicit reasoning showed better cultural grounding than models that were simply larger. All data, prompts, and code are public, giving researchers a basis for culture-aware multimodal work on Arabic.

Key points

  • Pearl holds more than 309K multimodal examples across ten domains, including food, architecture, music, clothes, flora, fauna, celebrations, handcrafts, landmarks and geography. It was created by 37 annotators, all credited as authors.
  • Pearl-X began with about 100 candidate shared concepts, which manual filtering cut to 61 (for example kabsa, found in seven countries). Each concept appears in at least two Arab countries and has roughly three images, for 347 images in total.
  • Pearl-X contains 367 MCQ and True/False questions: 177 use a single image and 190 use multiple images. ChatGPT-o3 drafted them from hand-written templates, and humans then checked every question.
  • On Pearl-X, o3-2025-04-16 scored highest at 78.75%. Qwen2.5-VL-72B-Instruct was the best open model at 73.57%. Reasoning-centric models generally outperformed their counterparts.
  • Images come from Wikipedia under Creative Commons licenses. Images from other sources were masked or regenerated with different identities. The data is available at github.com/UBC-NLP/pearl.

Interesting ideas

  • I1. Pearl-X tests a model on one shared concept shown in different regional forms, with both single-image and cross-image comparison questions, so it can tell real understanding of differences from generic recognition.
  • I2. Questions are grouped by the kind of reasoning they require (cause and effect, chronological order, perspective shifting, scenario completion), not only by topic, so accuracy can be broken down by skill.
  • I3. The pipeline over-generates candidates, discards most of them through human filtering (100 concepts down to 61), and has every generated question reviewed. Cheap generation plus strict acceptance keeps quality high.
  • I4. Hand-written question templates are filled in by a strong model given the concept name and the images, which constrains the form of the output while letting the model supply content.
  • I5. The authors release a lighter benchmark (Pearl-Lite) next to the full one, so quick evaluations can be run before costly full runs.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (world): We could build contrast sets in which the same frame type, such as a gift or a trade, appears with different participants and states, and check that the text world keeps each variant separate instead of merging them.
  • I2 (answer): Tagging fable and school-test questions with these reasoning types would show whether failures cluster in event ordering, causal links, or viewpoint changes.
  • I3 (learn): LLM teacher tiers could propose many silver frames or QA items, with only those that pass witness-parser agreement or a human spot check entering training data.
  • I4 (answer): Templates applied over entities and events in a text's world graph could produce controlled comprehension questions whose correct answers are known from the graph itself.
  • I5 (learn): A small fixed "lite" regression suite with negative controls could gate each parser or repair-rule change before the full evaluation runs.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 worksSocial Sciences · 1,772 worksEducation · 203 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 2,908 worksVision & language · 657 works

Cite

Cite as Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki, Omer Nacar, Youssef Nafea, Safaa Taher Abdelfadil, Abdulfattah Mohammed Yahya, Hamzah Luqman, Nada Almarwani, Samah Aloufi, Baraah Qawasmeh, Houdaifa Atou, Serry Sibaee, Hamzah A. Alsayadi, Walid Al-Dhabyani, Maged S. Al-shaibani, Aya El aatar, Nour Qandos, Rahaf Alhamouri, Samar Ahmad, Mohammed Anwar AL-Ghrawi, Aminetou Yacoub, Ruwa AbuHweidi, Vatimetou Mohamed Lemin, Reem Abdel-Salam, Ahlam Bashiti, Adel Ammar, Aisha Alansari, Ahmed Ashraf, Nora Alturayeif, Alcides Alcoba Inciarte, AbdelRahim A. Elmadany, Mohamedou Cheikh Tourad, Ismail Berrada, Mustafa Jarrar, Shady Shehata and Muhammad Abdul-Mageed. 2025. Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset. Findings of the Association for Computational Linguistics: EMNLP 2025.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.findings-emnlp.1254

@inproceedings{alwajih2025pearl,
  title = {{Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset}},
  author = {Fakhraddin Alwajih, Samar M. Magdy, Abdellah {El Mekki}, Omer Nacar, Youssef Nafea, Safaa Taher Abdelfadil, Abdulfattah Mohammed Yahya, Hamzah Luqman, Nada Almarwani, Samah Aloufi, Baraah Qawasmeh, Houdaifa Atou, Serry Sibaee, Hamzah A. Alsayadi, Walid Al-Dhabyani, Maged S. Al-shaibani, Aya {El aatar}, Nour Qandos, Rahaf Alhamouri, Samar Ahmad, Mohammed Anwar AL-Ghrawi, Aminetou Yacoub, Ruwa AbuHweidi, Vatimetou Mohamed Lemin, Reem Abdel-Salam, Ahlam Bashiti, Adel Ammar, Aisha Alansari, Ahmed Ashraf, Nora Alturayeif, Alcides Alcoba Inciarte, AbdelRahim A. Elmadany, Mohamedou Cheikh Tourad, Ismail Berrada, Mustafa Jarrar, Shady Shehata and Muhammad Abdul-Mageed},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},
  year = {2025},
  doi = {10.18653/v1/2025.findings-emnlp.1254},
  url = {https://doi.org/10.18653/v1/2025.findings-emnlp.1254}
}

References

56 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Manel Aloui, Hasna Chouikhi, Ghaith Chaabane, Haithem Kchaou, and Chehir Dhaouadi. 2024. 101 billion arabic words dataset. arXiv preprint arXiv:2405.01590. ↗
  2. Fakhraddin Alwajih, El Moatez Billah Nagoudi, Gagan Bhatia, Abdelrahman Mohamed, and Muhammad Abdul-Mageed. 2024. Peacock: A family of arabic multimodal large language models and benchmarks. arXiv preprint arXiv:2403.01031. ↗
  3. Zaid Alyafeai, Khalid Almubarak, Ahmed Ashraf, Deema Alnuhait, Saied Alshahrani, Gubran AQ Abdulrahman, Gamil Ahmed, Qais Gawah, Zead Saleh, Mustafa Ghaleb, and 1 others. 2024. Cidar: Culturally relevant instruction dataset for arabic. arXiv preprint arXiv:2402.03177. ↗
  4. Amith Ananthram, Elias Stengel-Eskin, Carl Vondrick, Mohit Bansal, and Kathleen McKeown. 2024. See it from my perspective: Diagnosing the western cultural bias of large vision-language models in image understanding. arXiv preprint arXiv:2406.11665. ↗
  5. Anthropic. 2025. System card: Claude opus 4 & claude sonnet 4. System card, Anthropic. find
  6. Yujin Baek, ChaeHun Park, Jaeseok Kim, Yu-Jung Heo, Du-Seong Chang, and Jaegul Choo. 2024. Evaluating visual and cultural interpretation: The k-viscuit benchmark with human-vlm collaboration. arXiv preprint arXiv:2406.16469. ↗
  7. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report ↗
  8. Federico Becattini, Pietro Bongini, Luana Bulla, Alberto Del Bimbo, Ludovica Marinucci, Misael Mongiovì, and Valentina Presutti. 2023. Viscounth: a large-scale multilingual visual question answering dataset for cultural heritage. ACM Transactions on Multimedia Computing, Communications and Applications, 19(6):1–20. ↗
  9. Mehar Bhatia, Sahithya Ravi, Aditya Chinchure, Eunjeong Hwang, and Vered Shwartz. 2024. From local concepts to universals: Evaluating the multicultural understanding of vision-language models. arXiv preprint arXiv:2407.00263. https://alliancecan.ca https://arc.ubc.ca/ubc-arc-sockeye ↗
  10. Olena Burda-Lassen, Aman Chadha, Shashank Goswami, and Vinija Jain. 2024. How culturally aware are vision-language models? arXiv preprint arXiv:2405.17475. ↗
  11. Olena Burda-Lassen, Aman Chadha, Shashank Goswami, and Vinija Jain. 2025. How culturally aware are vision-language models? In 2025 IEEE 6th International Conference on Image Processing, Applications and Systems (IPAS), pages 1–6. IEEE. find
  12. Soravit Changpinyo, Linting Xue, Michal Yarom, Ashish V Thapliyal, Idan Szpektor, Julien Amelot, Xi Chen, and Radu Soricut. 2022. Maxm: Towards multilingual visual question answering. arXiv preprint arXiv:2209.05401. ↗
  13. Boyuan Chen, Zhuo Xu, Sean Kirmani, Brain Ichter, Dorsa Sadigh, Leonidas Guibas, and Fei Xia. 2024. Spatialvlm: Endowing vision-language models with spatial reasoning capabilities. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14455–14465. find
  14. Rocktim Jyoti Das, Simeon Emilov Hristov, Haonan Li, Dimitar Iliyanov Dimitrov, Ivan Koychev, and Preslav Nakov. 2024. Exams-v: A multi-discipline multilingual multimodal exam benchmark for evaluating vision language models. arXiv preprint arXiv:2403.10378. ↗
  15. Saurabh Dash, Yiyang Nan, John Dang, Arash Ahmadian, Shivalika Singh, Madeline Smith, Bharat Venkitesh, Vlad Shmyhlo, Viraat Aryabumi, Walter Beller-Morales, and 1 others. 2025. Aya vision: Advancing the frontier of multilingual multimodality. arXiv preprint arXiv:2505.08751. ↗
  16. Google DeepMind. 2025. Gemini 2.5 pro. Vertex AI Documentation. Accessed May 18, 2025. find
  17. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Dingjie Song, Zhihong Chen, Abdulmohsen Alharthi, Bang An, Ziche Liu, and 1 others. 2023. Acegpt, localizing large language models in arabic. arXiv preprint arXiv:2309.12053. ↗
  18. Karima Kadaoui, Hanin Atwany, Hamdan Al-Ali, Abdelrahman Mohamed, Ali Mekky, Sergei Tilga, Natalia Fedorova, Ekaterina Artemova, Hanan Aldarmaki, and Yova Kementchedjhieva. 2025. Jeem: Vision-language understanding in four arabic dialects. arXiv preprint arXiv:2503.21910. ↗
  19. Chen Cecilia Liu, Iryna Gurevych, and Anna Korhonen. 2025a. Culturally aware and adapted nlp: A taxonomy and a survey of the state of the art. Transactions of the Association for Computational Linguistics, 13:652– 689. ↗
  20. Fangyu Liu, Emanuele Bugliarello, Edoardo Maria Ponti, Siva Reddy, Nigel Collier, and Desmond Elliott. 2021. Visually grounded reasoning across languages and cultures. arXiv preprint arXiv:2109.13238. ↗
  21. Shudong Liu, Yiqiao Jin, Cheng Li, Derek F Wong, Qingsong Wen, Lichao Sun, Haipeng Chen, Xing Xie, and Jindong Wang. 2025b. Culturevlm: Characterizing and improving cultural understanding of vision-language models for over 100 countries. arXiv preprint arXiv:2501.01282. ↗
  22. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, and 1 others. 2025c. Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233. Springer.
  23. Sara Ghaboura, Ahmed Heakl, Omkar Thawakar, Ali Alharthi, Ines Riahi, Abduljalil Saif, Jorma Laaksonen, Fahad S. Khan, Salman Khan, and Rao M. Anwer. 2024. Camel-bench: A comprehensive arabic lmm benchmark. Preprint, arXiv:2410.18976. ↗
  24. Zheng Ma, Mianzhi Pan, Wenhan Wu, Kanzhi Cheng, Jianbing Zhang, Shujian Huang, and Jiajun Chen. 2023. Food-500 cap: A fine-grained food caption benchmark for evaluating vision-language models. In Proceedings of the 31st ACM International Conference on Multimedia, pages 5674–5685. find
  25. Xiaotian Han, Quanzeng You, Yongfei Liu, Wentao Chen, Huangjie Zheng, Khalil Mrini, Xudong Lin, Yiqi Wang, Bohan Zhai, Jianbo Yuan, and 1 others. 2023. Infimm-eval: Complex open-ended reasoning evaluation for multi-modal large language models. arXiv preprint arXiv:2311.11567. ↗
  26. Shravan Nayak, Kanishk Jain, Rabiul Awal, Siva Reddy, Sjoerd Van Steenkiste, Lisa Anne Hendricks, Aishwarya Agrawal, and 1 others. 2024. Benchmarking vision language models for cultural understanding. arXiv preprint arXiv:2407.10920. ↗
  27. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300. ↗
  28. Quan Van Nguyen, Dan Quang Tran, Huy Quang Pham, Thang Kien-Bao Nguyen, Nghia Hieu Nguyen, Kiet Van Nguyen, and Ngan Luu-Thuy Nguyen. 2024. Vitextvqa: A large-scale visual question answering dataset for evaluating vietnamese text comprehension in images. Preprint, arXiv:2404.10652. ↗
  29. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, and 1 others. 2024. Acegpt, localizing large language models in arabic. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8132–8156.
  30. Shota Onohara, Atsuyuki Miyai, Yuki Imajuku, Kazuki Egashira, Jeonghun Baek, Xiang Yue, Graham Neubig, and Kiyoharu Aizawa. 2024. Jmmmu: A japanese massive multi-discipline multimodal understanding benchmark for culture-aware evaluation. Preprint, arXiv:2410.17250. ↗
  31. OpenAI. 2025. OpenAI o3 and o4-mini System Card. Technical report, OpenAI. Version 2 of the Preparedness Framework. find
  32. Patrick E Shrout and Joseph L Fleiss. 1979. Intraclass correlations: uses in assessing rater reliability. Psychological bulletin, 86(2):420. ↗
  33. Shantipriya Parida, Idris Abdulmumin, Shamsuddeen Hassan Muhammad, Aneesh Bose, Guneet Singh Kohli, Ibrahim Said Ahmad, Ketan Kotwal, Sayan Deb Sarkar, Ondřej Bojar, and Habeebah Kakudi. 2023. HaVQA: A dataset for visual question answering and multimodal research in Hausa language. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10162–10183, Toronto, Canada. Association for Computational Linguistics. ↗
  34. Shivalika Singh, Angelika Romanou, Clémentine Fourrier, David I Adelani, Jian Gang Ngui, Daniel Vila-Suero, Peerat Limkonchotiwat, Kelly Marchisio, Wei Qi Leong, Yosephine Susanto, and 1 others. 2024. Global mmlu: Understanding and addressing cultural and linguistic biases in multilingual evaluation. arXiv preprint arXiv:2412.03304. ↗
  35. Siddhesh Pawar, Junyeong Park, Jiho Jin, Arnav Arora, Junho Myung, Srishti Yadav, Faiz Ghifari Haznitrama, Inhwa Song, Alice Oh, and Isabelle Augenstein. 2024. Survey of cultural awareness in language models: Text and beyond. arXiv preprint arXiv:2411.00860. ↗
  36. Siddhesh Pawar, Junyeong Park, Jiho Jin, Arnav Arora, Junho Myung, Srishti Yadav, Faiz Ghifari Haznitrama, Inhwa Song, Alice Oh, and Isabelle Augenstein. 2025. Survey of cultural awareness in language models: Text and beyond. Computational Linguistics, pages 1–96. ↗
  37. Jonas Pfeiffer, Gregor Geigle, Aishwarya Kamath, Jan-Martin O Steitz, Stefan Roth, Ivan Vulić, and Iryna Gurevych. 2021. xgqa: Cross-lingual visual question answering. arXiv preprint arXiv:2109.06082. ↗
  38. David Romero, Chenyang Lyu, Haryo Akbarianto Wibowo, Teresa Lynn, Injy Hamed, Aditya Nanda Kishore, Aishik Mandal, Alina Dragonetti, Artem Abzaliev, Atnafu Lambebo Tonja, and 1 others. 2024. Cvqa: Culturally-diverse multilingual visual question answering benchmark. arXiv preprint arXiv:2406.05967. ↗
  39. Florian Schneider, Carolin Holtermann, Chris Biemann, and Anne Lauscher. 2025. Gimmick–globally inclusive multimodal multitask cultural knowledge benchmarking. arXiv preprint arXiv:2502.13766. ↗
  40. Xiujie Song, Mengyue Wu, Kenny Q. Zhu, Chunhao Zhang, and Yanyi Chen. 2025. A cognitive evaluation benchmark of image reasoning and description for large vision-language models. Preprint, arXiv:2402.18409. ↗
  41. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, and 1 others. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. ↗
  42. Maxim Tkachenko, Mikhail Malyuk, Andrey Holmanyuk, and Nikolai Liubimov. 2020. Label studio: Data labeling software. Open source software available from https://github.com/heartexlabs/labelstudio, 2022. ↗
  43. Ashmal Vayani, Dinura Dissanayake, Hasindri Watawana, Noor Ahsan, Nevasini Sasikumar, Omkar Thawakar, Henok Biadglign Ademtew, Yahya Hmaiti, Amandeep Kumar, Kartik Kuckreja, and 1 others. 2024. All languages matter: Evaluating lmms on culturally diverse 100 languages. arXiv preprint arXiv:2411.16508. ↗
  44. Hongyu Wang, Jiayu Xu, Senwei Xie, Ruiping Wang, Jialin Li, Zhaojie Xie, Bin Zhang, Chuyan Xiong, and Xilin Chen. 2024a. M4u: Evaluating multilingual understanding and reasoning for large multimodal models. arXiv preprint arXiv:2405.15638. ↗
  45. Florian Schneider and Sunayana Sitaram. 2024. M5– a diverse benchmark to assess the performance of large multimodal models across multilingual and multicultural vision-language tasks. arXiv preprint arXiv:2407.03791. ↗
  46. Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Sharon Li, and Neel Joshi. 2024b. Is a picture worth a thousand words? delving into spatial reasoning for vision language models. Advances in Neural Information Processing Systems, 37:75392– 75421. find
  47. Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, Osama Mohammed Afzal, Samta Kamboj, Onkar Pandit, Rahul Pal, and 1 others. 2023. Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models. arXiv preprint arXiv:2308.16149. ↗
  48. Sibo Wang, Xiangkui Cao, Jie Zhang, Zheng Yuan, Shiguang Shan, Xilin Chen, and Wen Gao. 2024c. Vlbiasbench: A comprehensive benchmark for evaluating bias in large vision-language model. Preprint, arXiv:2406.14194. ↗
  49. Hao Shao, Shengju Qian, Han Xiao, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu, and Hongsheng Li. 2024. Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. In Advances in Neural Information Processing Systems, volume 37, pages 8612–8642. Curran Associates, Inc. find
  50. Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, and 1 others. 2025. Internvl3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265. ↗
  51. Yiqi Wang, Wentao Chen, Xiaotian Han, Xudong Lin, Haiteng Zhao, Yongfei Liu, Bohan Zhai, Jianbo Yuan, Quanzeng You, and Hongxia Yang. 2024d. Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning. arXiv preprint arXiv:2401.06805. ↗
  52. Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan, David Anugraha, Rifki Afina Putri, Yutong Wang, Adam Nohejl, Ubaidillah Ariq Prathama, Nedjma Ousidhoum, Afifa Amriani, Anar Rzayev, Anirban Das, Ashmari Pramodya, Aulia Adila, Bryan Wilie, Candy Olivia Mawalim, Ching Lam Cheng, Daud Abolade, Emmanuele Chersoni, and 32 others. 2024. Worldcuisines: A massive-scale benchmark for multilingual and multicultural visual question answering on global cuisines. Preprint, arXiv:2410.12705. ↗
  53. Kaining Ying, Fanqing Meng, Jin Wang, Zhiqian Li, Han Lin, Yue Yang, Hao Zhang, Wenbo Zhang, Yuqi Lin, Shuo Liu, Jiayi Lei, Quanfeng Lu, Runjian Chen, Peng Xu, Renrui Zhang, Haozhe Zhang, Peng Gao, Yali Wang, Yu Qiao, and 3 others. 2024. Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi. Preprint, arXiv:2404.16006. ↗
  54. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490. ↗
  55. Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, and 3 others. 2024. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. Preprint, arXiv:2311.16502. ↗
  56. Wenxuan Zhang, Mahani Aljunied, Chang Gao, Yew Ken Chia, and Lidong Bing. 2023. M3exam: A multilingual, multimodal, multilevel benchmark for examining large language models. Advances in Neural Information Processing Systems, 36:5484–5505. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/alwajih-2025-pearl-multimodal-culturally-aware-arabic/