The Multilingual Divide and Its Impact on Global AI Safety

• URL: http://arxiv.org/abs/2505.21344v1
• Date: Tue, 27 May 2025 15:37:32 GMT
• Title: The Multilingual Divide and Its Impact on Global AI Safety
• Authors: Aidan Peppin, Julia Kreutzer, Alice Schoenauer Sebag, Kelly Marchisio, Beyza Ermis, John Dang, Samuel Cahyawijaya, Shivalika Singh, Seraphina Goldfarb-Tarrant, Viraat Aryabumi, Aakanksha, Wei-Yin Ko, Ahmet Üstün, Matthias Gallé, Marzieh Fadaee, Sara Hooker,
• Abstract summary: This paper provides researchers, policymakers and governance experts with an overview of key challenges to bridging the "language gap" in AI.<n>We provide an analysis of why the language gap in AI exists and grows, and how it creates disparities in global AI safety.
• Score: 27.639490480528337
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right [0.0]
  This work examines the security of LMs for lower- and medium-resourced languages.<n>We extend existing adversarial attacks for up to 70 languages to evaluate the security of monolingual and multilingual LMs for these languages.
  arXiv  Detail & Related papers  (2025-07-04T10:54:04Z)
• The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It [21.6479207553511]
  We review nearly 300 publications from 2020--2024 across major NLP conferences and workshops at *ACL.<n>We observe that non-English languages are rarely studied as a standalone language and that English safety research exhibits poor language documentation practice.<n>Based on our survey and proposed directions, the field can develop more robust, inclusive AI safety practices for diverse global populations.
  arXiv  Detail & Related papers  (2025-05-30T01:32:44Z)
• MPO: Multilingual Safety Alignment via Reward Gap Optimization [88.76638442683391]
  Large language models (LLMs) have become increasingly central to AI applications worldwide.<n>Existing preference learning methods for safety alignment, such as RLHF and DPO, are primarily monolingual and struggle with noisy multilingual data.<n>We introduce Multilingual reward gaP Optimization (MPO), a novel approach that leverages the well-aligned safety capabilities of the dominant language (English) to improve safety alignment across multiple languages.
  arXiv  Detail & Related papers  (2025-05-22T16:24:51Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.79292318645454]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• Uncovering inequalities in new knowledge learning by large language models across different languages [66.687369838071]
  We show that low-resource languages consistently face disadvantages across all four dimensions.<n>We aim to raise awareness of linguistic inequalities in LLMs' new knowledge learning, fostering the development of more inclusive and equitable future LLMs.
  arXiv  Detail & Related papers  (2025-03-06T03:41:47Z)
• Generative AI and Large Language Models in Language Preservation: Opportunities and Challenges [0.0]
  Generative AI (GenAI) and Large Language Models (LLMs) unlock new frontiers in automating corpus creation, transcription, translation, and tutoring.<n>This paper introduces a novel analytical framework that systematically evaluates GenAI applications against language-specific needs.<n>We demonstrate its efficacy through the Te Reo M=aori revitalization, where it illuminates successes, such as community-led Automatic Speech Recognition achieving 92% accuracy.<n>Our findings underscore that GenAI can indeed revolutionize language preservation, but only when interventions are rigorously anchored in community-centric data stewardship, continuous evaluation, and transparent risk management.
  arXiv  Detail & Related papers  (2025-01-20T14:03:40Z)
• A Capabilities Approach to Studying Bias and Harm in Language Technologies [4.135516576952934]
  We consider fairness, bias, and inclusion in Language Technologies through the lens of the Capabilities Approach. The Capabilities Approach centers on what people are capable of achieving, given their intersectional social, political, and economic contexts. We detail the Capabilities Approach, its relationship to multilingual and multicultural evaluation, and how the framework affords meaningful collaboration with community members in defining and measuring the harms of Language Technologies.
  arXiv  Detail & Related papers  (2024-11-06T22:46:13Z)
• Towards Safe Multilingual Frontier AI [0.18957478338649109]
  multilingual jailbreaks undermine the safe and inclusive deployment of AI systems. We propose policy actions that align with the EU legal landscape and institutional framework to address multilingual jailbreaks. These include mandatory assessments of multilingual capabilities and vulnerabilities, public opinion research, and state support for multilingual AI development.
  arXiv  Detail & Related papers  (2024-09-06T14:26:18Z)
• Safe Multi-agent Reinforcement Learning with Natural Language Constraints [49.01100552946231]
  The role of natural language constraints in Safe Multi-agent Reinforcement Learning (MARL) is crucial, yet often overlooked. We propose a novel approach named Safe Multi-agent Reinforcement Learning with Natural Language constraints (SMALL) Our method leverages fine-tuned language models to interpret and process free-form textual constraints, converting them into semantic embeddings. These embeddings are then integrated into the multi-agent policy learning process, enabling agents to learn policies that minimize constraint violations while optimizing rewards.
  arXiv  Detail & Related papers  (2024-05-30T12:57:35Z)
• A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers [51.8203871494146]
  The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing.<n>Despite the breakthroughs of LLMs, the investigation into the multilingual scenario remains insufficient.<n>This survey aims to help the research community address multilingual problems and provide a comprehensive understanding of the core concepts, key techniques, and latest developments in multilingual natural language processing based on LLMs.
  arXiv  Detail & Related papers  (2024-05-17T17:47:39Z)
• CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion [117.178835165855]
  This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs. Our studies reveal a new and universal safety vulnerability of these models against code input. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization.
  arXiv  Detail & Related papers  (2024-03-12T17:55:38Z)
• Text Embedding Inversion Security for Multilingual Language Models [2.790855523145802]
  Research shows that text can be reconstructed from embeddings, even without knowledge of the underlying model. This study is the first to investigate multilingual inversion attacks, shedding light on the differences in attacks and defenses across monolingual and multilingual settings.
  arXiv  Detail & Related papers  (2024-01-22T18:34:42Z)
• All Languages Matter: On the Multilingual Safety of Large Language Models [96.47607891042523]
  We build the first multilingual safety benchmark for large language models (LLMs) XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We propose several simple and effective prompting methods to improve the multilingual safety of ChatGPT.
  arXiv  Detail & Related papers  (2023-10-02T05:23:34Z)

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.