GPT-2 Reportedly Reproduced Personal Data from Its Training Data

Summary

OpenAI's GPT-2 reportedly memorized and reproduced portions of its training data, including personal information such as names, email addresses, social media handles, and phone numbers. Researchers raised concerns that large language models could expose private or sensitive information when trained on web-scale datasets containing personal data.

Developers

• OpenAI

Deployers

• OpenAI

Harmed parties

• People whose personal data was included in GPT-2 training data
• GPT-2 users
• Privacy
• Biometric data subjects