Urgent.News

What's breaking now, across thousands of outlets.

AI

Nigerian AI Researcher Exposes Pidgin Blind Spot in OpenAI, Google

Stories by Emma Okonji The Meaning Intelligence Lab, an independent research initiative that was unveiled at the recent World Public Relations Forum (WPRF 2026) in Abuja by Dr. Celestine Achi,

Dr. Celestine Achi, a Nigerian Artificial Intelligence (AI) researcher, has unveiled a significant blind spot in AI models' ability to recognize Pidgin language through an independent research initiative called The Meaning Intelligence Lab. This discovery was unveiled at the World Public Relations Forum (WPRF 2026) in Abuja. The study, which analyzed 500 Nigerian posts, news excerpts, and speeches in Standard English, Nigerian English, Nigerian Pidgin, and code-mixed speech, revealed that frontier AI models scored as low as 11 percent on Pidgin recognition.

Human analysts, on the other hand, scored an impressive 92 percent. The Meaning Intelligence Lab addressed this issue by providing three AI models with a single paragraph of linguistic guidance on how Pidgin grammar works. This simple intervention lifted the AI models' Pidgin recognition accuracy to between 90 and 96 percent, matching the performance of human analysts.

Written by urgent.news from This Day's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at thisdaylive.com →

More in AI

More from Wednesday 18 November →