- A Stanford University study found that AI-detection systems incorrectly label essays from non-native English speakers as bot-generated.
- One system misidentified nearly 98% of such essays as AI-generated, whereas correctly identified only 20% of the essays of native English speakers as AI-generated.
- Researchers attribute this discrepancy to systemic bias in AI-detection system’s metric ‘text perplexity’ which measures the surprise in word choices, causing undue harm to non-native English speakers.
Menu
