mlsanityData to 14 Oct 2026

The Multilingual Divide and Its Impact on Global AI Safety

arXiv 2505.21344 ↗First posted 27 May 2025cs.AI cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Despite advances in large language model capabilities in recent years, a large gap remains in their capabilities and safety performance for many languages beyond a relatively small handful of globally dominant languages. This paper provides researchers, policymakers and governance experts with an overview of key challenges to bridging the "language gap" in AI and minimizing safety risks across languages. We provide an analysis of why the language gap in AI exists and grows, and how it creates disparities in global AI safety. We identify barriers to address these challenges, and recommend how those working in policy and governance can help address safety concerns associated with the language gap by supporting multilingual dataset creation, transparency, and research.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 72 of its 105 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

72 of 105 references.

References · 72

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  7. 2020Learning to summarize from human feedbackcited by 2,588
  8. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  9. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  10. 2021Ethical and social risks of harm from Language Modelscited by 966
  11. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  12. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
38 more
  1. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  2. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
  3. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  4. 2022Beyond neural scaling laws: beating power law scaling via data pruningcited by 528
  5. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  6. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 387
  7. 2023Low-Resource Languages Jailbreak GPT-4cited by 309
  8. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 295
  9. 2024Do Llamas Work in English? On the Latent Language of Multilingual Transformerscited by 281
  10. 2023Multilingual Jailbreak Challenges in Large Language Modelscited by 240
  11. 2023Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Modelscited by 192
  12. 2023Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedbackcited by 190
  13. 2021Visually Grounded Reasoning across Languages and Culturescited by 189
  14. 2023Gender bias and stereotypes in Large Language Modelscited by 187
  15. 2023Having Beer after Prayer? Measuring Cultural Bias in Large Language Modelscited by 153
  16. 2024Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontiercited by 129
  17. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmarkcited by 120
  18. 2021Gender Bias in Machine Translationcited by 117
  19. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 104
  20. 2024The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contextscited by 94
  21. 2024MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answeringcited by 93
  22. 2022Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Modelscited by 92
  23. 2020Low-resource Languages: A Review of Past Work and Future Challengescited by 91
  24. 2024INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledgecited by 86
  25. 2024Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Modelscited by 84
  26. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  27. 2023The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AIcited by 73
  28. 2021xGQA: Cross-Lingual Visual Question Answeringcited by 72
  29. 2021Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translationcited by 70
  30. 2024The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harmcited by 70
  31. 2022NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languagescited by 68
  32. 2022One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesiacited by 66
  33. 2024Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languagescited by 64
  34. 2023Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capabilitycited by 62
  35. 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
  36. 2024IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languagescited by 52
  37. 2023Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languagescited by 51
  38. 2024M-RewardBench: Evaluating Reward Models in Multilingual Settingscited by 50

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 6.

10 papers.

  1. 2025The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating Itcited by 45
  2. 2026When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Trainingcited by 5
  3. 2025CoPE: A Small Language Model for Steerable and Scalable Content Labelingcited by 4
  4. 2025Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justicecited by 2
  5. 2026The Culture Funnel: You Can't Align What isn't in the Datacited by 2
  6. 2025BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culturecited by 1
  7. 2026Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global Southcited by 1
  8. 2026BYOL: Bring Your Own Language Into LLMscited by 0
  9. 2026A Translational Note on AI Safety Evaluationcited by 0
  10. 2026Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoningcited by 0