# Should There be a Teacher In-the-Loop? A Study of Generative AI-Personalized Tasks Middle School

DevFeed: [Should There be a Teacher In-the-Loop? A Study of Generative AI-Personalized Tasks Middle School](<https://devfeed.tech/articles/should-there-be-a-teacher-in-the-loop-a-study-of-generative-ai-personalized-tasks-middle-school-131883.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.15876>)

Author: Candace Walkington, Mingyu Feng, Itffini Pruitt-Britton, Theodora Beauchamp, Andrew Lan

Published: 2026-11-13T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [culture](<https://devfeed.tech/tags/culture.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [ethics](<https://devfeed.tech/tags/ethics.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [in-the-loop](<https://devfeed.tech/tags/in-the-loop.md>), [interest](<https://devfeed.tech/tags/interest.md>), [learning](<https://devfeed.tech/tags/learning.md>), [mathematics](<https://devfeed.tech/tags/mathematics.md>), [models](<https://devfeed.tech/tags/models.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [size](<https://devfeed.tech/tags/size.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

## AI overview

In a study of 7 middle school mathematics teachers using ChatGPT to personalize curriculum problems, teacher involvement helped tailor tasks but often at a broad level. Students often preferred specific popular culture references matching their interests. Teachers prompted the model to revise references and address problems with depth, ethics, and realism; some exercised epistemic agency. The study also examined teacher efficiency and student ratings, but the supplied abstract gives no results for those measures. Its conclusions are based on this sample, and its discussion of scalability is exploratory.

## Source excerpt

arXiv:2602.15876v2 Announce Type: replace-cross Abstract: Large language models can be used to design instructional tasks to align to students needs. These generative AI models can create tasks that correspond to students out-of-school interests in areas like sports or music, which may enhance students interest in learning. However, little is known about teachers processes for creating or modifying tasks with generative AI, despite commercial AI companies claims that they will save teachers time. In the present study, 7 middle school mathematics teachers used ChatGPT to create personalized versions of problems in their curriculum to correspond to their students interests. The prompting moves teachers made and their students open-ended feedback on personalized problems were examined through thematic analysis. Teachers efficiency when creating problems and the ratings of their 7th grade students who received personalized assignments were examined. Results from this sample suggest that having a teacher-in-the-loop may result in generative AI-enhanced personalization being enacted at a broad grain size, whereas students often expressed preference for a smaller grain-size where they receive specific popular culture references that interest them. Teachers used prompting to adjust popular culture references and address issues with the depth, ethics, or realism of the problems generated, in some cases showing epistemic agency. The article closes with an exploratory, design-focused look at scalability trade-offs with teacher-facing personalization, patterns of teacher prompting practices, and opportunities for teachers to exercise epistemic and ethical monitoring of personalization outputs.