# Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

arXiv: https://arxiv.org/abs/2410.16153 · HTML: https://mlsanity.com/paper/2410.16153/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 43 of its 82 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 43)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [PaLI-X: On Scaling up a Multilingual Vision and Language Model](https://mlsanity.com/paper/2305.18565/) (2023)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models](https://mlsanity.com/paper/2402.11684/) (2024)
- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning](https://mlsanity.com/paper/2306.04387/) (2023)
- [Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation](https://mlsanity.com/paper/2401.06591/) (2024)
- [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark](https://mlsanity.com/paper/2406.05967/) (2024)

## Built on by (most cited first, 30 of 64)

- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [Meta CLIP 2: A Worldwide Scaling Recipe](https://mlsanity.com/paper/2507.22062/) (2025)
- [MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models](https://mlsanity.com/paper/2410.17578/) (2024)
- [JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation](https://mlsanity.com/paper/2410.17250/) (2024)
- [CAMEL-Bench: A Comprehensive Arabic LMM Benchmark](https://mlsanity.com/paper/2410.18976/) (2024)
- [TigerLLM - A Family of Bangla Large Language Models](https://mlsanity.com/paper/2503.10995/) (2025)
- [Grounding Multilingual Multimodal LLMs With Cultural Knowledge](https://mlsanity.com/paper/2508.07414/) (2025)
- [Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users](https://mlsanity.com/paper/2503.22610/) (2025)
- [The Multilingual Divide and Its Impact on Global AI Safety](https://mlsanity.com/paper/2505.21344/) (2025)
- [AIN: The Arabic INclusive Large Multimodal Model](https://mlsanity.com/paper/2502.00094/) (2025)
- [Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies](https://mlsanity.com/paper/2505.14972/) (2025)
- [Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models](https://mlsanity.com/paper/2506.13044/) (2025)
- [IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs](https://mlsanity.com/paper/2511.04727/) (2025)
- [MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding](https://mlsanity.com/paper/2505.20298/) (2025)
- [mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks](https://mlsanity.com/paper/2506.08400/) (2025)
- [VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models](https://mlsanity.com/paper/2411.19103/) (2024)
- [KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts](https://mlsanity.com/paper/2508.19944/) (2025)
- [TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla](https://mlsanity.com/paper/2509.09101/) (2025)
- [VARCO-VISION-2.0 Technical Report](https://mlsanity.com/paper/2509.10105/) (2025)
- [MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching](https://mlsanity.com/paper/2502.12852/) (2025)
- [OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA](https://mlsanity.com/paper/2510.06371/) (2025)
- [Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization](https://mlsanity.com/paper/2503.22577/) (2025)
- [AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model](https://mlsanity.com/paper/2510.11496/) (2025)
- [Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model](https://mlsanity.com/paper/2501.05122/) (2025)
- [xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation](https://mlsanity.com/paper/2503.09313/) (2025)
- [Behind Maya: Building a Multilingual Vision Language Model](https://mlsanity.com/paper/2505.08910/) (2025)
- [POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering](https://mlsanity.com/paper/2507.11939/) (2025)
- [FilBench: Can LLMs Understand and Generate Filipino?](https://mlsanity.com/paper/2508.03523/) (2025)
- [Finding Culture-Sensitive Neurons in Vision-Language Models](https://mlsanity.com/paper/2510.24942/) (2025)
- [Deep Temporal Reasoning in Video Language Models: A Cross-Linguistic Evaluation of Action Duration and Completion through Perfect Times](https://mlsanity.com/paper/2506.00928/) (2025)

## Abstract (arXiv)

Despite recent advances in multimodal large language models (MLLMs), their development has predominantly focused on English- and western-centric datasets and tasks, leaving most of the world's languages and diverse cultural contexts underrepresented. This paper introduces Pangea, a multilingual multimodal LLM trained on PangeaIns, a diverse 6M instruction dataset spanning 39 languages. PangeaIns features: 1) high-quality English instructions, 2) carefully machine-translated instructions, and 3) culturally relevant multimodal tasks to ensure cross-cultural coverage. To rigorously assess models' capabilities, we introduce PangeaBench, a holistic evaluation suite encompassing 14 datasets covering 47 languages. Results show that Pangea significantly outperforms existing open-source models in multilingual settings and diverse cultural contexts. Ablation studies further reveal the importance of English data proportions, language popularity, and the number of multimodal training samples on overall performance. We fully open-source our data, code, and trained checkpoints, to facilitate the development of inclusive and robust multilingual MLLMs, promoting equity and accessibility across a broader linguistic and cultural spectrum.