UW News
Shangbin Feng
August 28, 2024
Large language models can help detect social media bots — but can also make the problem worse
![A drawing of a robot with an empty speech bubble.](https://uw-s3-cdn.s3.us-west-2.amazonaws.com/wp-content/uploads/sites/6/2024/07/26102041/chatbot-6626193_1920-150x150.png)
A team led by University of Washington researchers found that large language models, such as ChatGPT, can make social media bots more sophisticated at evading detection. But these models can also improve systems that detect bots.