Israel Abebe Azime, Jesujoba O. Alabi, Iffat Maab, Alexander D. Cai, Tadesse Destaw Belay, Atnafu Lambebo Tonja, Jonas Kgomo, Folasade Alabi · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26474 · open-access PDF
Большие языковые модели (LLM), предназначенные для взаимодействия с пользователями, обычно обучаются адекватно реагировать на вредный или токсичный контент. Тем не менее, обеспечение адекватных ответов становится более сложным в различных языковых и культурных контекстах, где риски безопасности могут быть выражены или интерпретированы по-разному.
Machine translation (Meta M2M100); the English original follows.
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
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26474, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange