Mikel K. Ngueajio

The Alignment Gap: A Benchmark Demonstrating the Lack of Cross-Lingual Mapping in Dialect-Specialized Language Models - The Case of Ehugbo

This work introduces the first information retrieval benchmark resource for Ehugbo, a high-quality parallel multimodal corpus constructed from a high-quality parallel multimodal corpus that reveals the ''Alignment Gap'', where African-centric foundation models that excel at linguistic familiarity with Igbo achieve <5%...