It’s no secret that an ever-increasing number of scientists use AI to help with their papers. While tasks such as polishing text are generally permissible if declared, using the technology to write papers, or parts of papers, from scratch and passing them off as original work is not. But it’s happening.

As a result, editors and conference organizers are using AI detectors to spot AI use. However, these tools can make mistakes, which is far from ideal.

Step forward IdeaLens, a new kind of detector that looks at the ideas behind a text rather than the words themselves. Unlike Pangram and other AI detectors that examine word choices and sentence patterns, it looks for clues in the underlying ideas and arguments. The research is described in a paper posted to the arXiv preprint server.