AI Writing Detection Systems Misidentify Non-Native English Speakers As Bots

  • 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.
Join 2 million subscribers

A curated newsletter that summarizes the important news at the intersection of Global tech, India Tech and AI.

Delivered 8 AM. Daily.
nextbigwhat We would like to show you notifications for the latest news and updates.
Allow Notifications