AI models often fail to identify ableism across cultures

AI models often fail to identify ableism across cultures

The artificial intelligence models underlying popular chatbots and content moderation systems struggle to identify offensive, ableist social media posts in English—and perform even worse in Hindi, new Cornell research finds.

AI Misreads Disability Hate Across Cultures and South Asian Languages, Cornell Study Finds

Artificial intelligence systems built to detect hate speech are failing to recognize ableism across languages, according to new research from Cornell University. The study tested how eight large language models, both Western and Indian, handled disability-related comments in English and Hindi. The results showed deep cultural mismatches. How the study was done Researchers Mahika Phutane and Aditya Vashistha compared how 175 people with disabilit…