New Large-Language Model Can Protect Social Media Users' Privacy

Social media users may need to think twice before hitting that “Post” button.

A new large-language model (LLM) developed by Georgia Tech researchers can help them filter content that could risk their privacy and offer alternative phrasing that keeps the context of their posts intact.

According to a new paper that will be presented at the 2024 Association for Computing Linguistics(ACL) conference, social media users should tread carefully about the information they self-disclose in their posts.