Firstly, at GPTZero, we don't believe that any AI detector is perfect. There always exist edge cases with both instances where AI is classified as human, and human is classified as AI. Nonetheless, we recommend that educators can do the following when they get a positive detection:
- Ask students to demonstrate their understanding in a controlled environment, whether that is through an in-person assessment, or through an editor that can track their edit history (for instance, using our Writing Reports through Google Docs). Check out our list of several recommendations on types of assignments that are difficult to solve with AI.
- Ask the student if they can produce artifacts of their writing process, whether it is drafts, revision histories, or brainstorming notes. For example, if the editor they used to write the text has an edit history (such as Google Docs), and it was typed out with several edits over a reasonable period of time, it is likely the student work is authentic. You can use GPTZero's Writing Reports to replay the student's writing process, and view signals that indicate the authenticity of the work.
- See if there is a history of AI-generated text in the student's work. We recommend looking for a long-term pattern of AI use, as opposed to a single instance, in order to determine whether the student is using AI.
We believe that the best outcome for educators and students arrives by working together proactively to understand the problem of AI misuse and find strategies that hone in on the human value of education. For example, educators can:
- Help students understand the risks of using AI in their work (to learn more, see this article), and the value of learning to express themselves. For example, in real-life, real-time collaboration, pitching, and debate, how does your class improve their ability to communicate when AI is not available?
- Create an assessment that cannot be answered by ChatGPT or other AI. (See examples on the next slide)
- Ask students to produce multiple drafts of their work that they can revise as peers or through the educator, to help students understand that assignments are meant to teach a learning process.
- Ask students to produce work in a medium that is difficult to generate, such as PowerPoint presentations, visual displays, videos, or audio recordings.
- Set expectations for your students that you will be checking the work through an AI detector like GPTZero, to deter misuse of AI.
What are examples of assignments that cannot be answered by ChatGPT or other AI?
- Ask students to write about personal experiences and how they relate to the text, or reflect on their learning experience in your class.
- Ask students to critique the default answer given by ChatGPT to your question.
- Require that students cite real, primary sources of information to back up their specific claims, or ask them to write about recent events.
- Assess students based on a live discussion with their peers, and use peer assessment tools (such as the one provided by our partner, Peerceptiv).
- Ask students to complete their assignments in class or in an interactive way, and shift lectures to be take-home.