Israel Abebe Azime
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
AfriGuard: Safety and Robust Refusal For African Languages
According to the abstract, Israel Abebe Azime, Jesujoba O. Alabi, Iffat Maab and colleagues introduce AfriGuard, a dataset for studying harmful intent, safety-category understanding and refusal across 10 African languages and English. They report guardrail models underperform other LLMs, with models scoring below 60% F1 on understanding safety behavior.