Newest papers

AfriGuard: Safety and Robust Refusal For African Languages

Israel Abebe Azime, Jesujoba Oluwadara Alabi, Iffat Maab, Alexander D. Cai, Tadesse Destaw Belay, Atnafu Lambebo Tonja, Jonas Kgomo, Folasade Alabi, Salomey Osei, Saminu Muhammad Aliyu, Nkechinyere Faith Aguobi, Bontu Fufa Balcha, Blessing Sibanda, David S. Davis, Mouhamadane Mboup, Daud Olamide Abolade, Neo Putini, Louis Powell, Kiant'e Brantley, Philipp Slusallek · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26474 · cited by 0 works (OpenAlex) · open-access PDF

Korean

사용자와 상호 작용하도록 설계된 대형 언어 모델(LLM)은 일반적으로 유해 또는 독성 콘텐츠에 적절하게 대응하도록 훈련받습니다. 그러나, 적절한 응답을 보장하는 것은 다양한 언어 및 문화적 맥락에서 더 도전적이되며, 보안 위험이 다른 방식으로 표현되거나 해석될 수 있습니다. 안전한 AI 시스템을 구축하는 것은 보안 위험을 감지하고 그 성격을 이해하고 적절하게 대응하는 것이므로 각 단계에 복잡성을 추가하는 언어적 및 문화적 변화를 계산합니다. 이 작업에서 우리는 유해한 의도, 보안 범주 이해 및 아프리카 언어 10개에서 거부 행동을 연구하기위한 AfriGuard, 문화적으로 기초화된 다국어 데이터 세트를 소개합니다. 우리의

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) designed to interact with users are typically trained to respond appropriately to harmful or toxic content. However, ensuring appropriate responses becomes more challenging in diverse linguistic and cultural contexts, where safety risks may be expressed or interpreted differently. Building safe AI systems therefore requires detecting safety risks, understanding their nature, and responding appropriately, while accounting for linguistic and cultural variations that add complexity to each stage. In this work, we introduce AfriGuard, a culturally grounded multilingual dataset for studying harmful intent, safety-category understanding, and refusal behavior across 10 African languages and English. Our findings reveal that guardrail models underperform both open- and closed-source LLMs on safety-intent and safety-category classification, while models show limited understanding of appropriate safety behavior, scoring below 60% F1. We further find that models often fail to respond appropriately to unsafe prompts not because they explicitly refuse, but because they produce linguistically inadequate responses that result in incidental non-assistance rather than proper refusals. Finally, using AfriGuard, we develop efficient guardrail models that achieve performance competitive with models up to 30x larger, introduce refusal detectors that improve average performance by 43.9% over existing detectors, and demonstrate that supervised fine-tuning can substantially improve overall safety performance.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Cultural diversity, Risk analysis (engineering), Psychology, Human factors and ergonomics, Risk assessment

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange