← 연구 뉴스로 돌아가기
Editorial cover for LLM feedback inside an intelligent tutoring system
저널 논문Peer-reviewed study20252026년 6월 23일· 8 min

Generating In-Context, Personalized Feedback for Intelligent Tutors with Large Language Models

Jennifer M. Reddig, Arav Arora, Christopher J. MacLellan

International Journal of Artificial Intelligence in Education

500단어 요약

Editorial cover for LLM feedback inside an intelligent tutoring system

Reddig, Arora, and MacLellan study a question that sits directly at the current boundary between classic intelligent tutoring systems and generative AI: can a large language model generate useful, in-context feedback for learners inside an ITS? The paper focuses on GPT-4 and the Apprentice Tutor College Algebra ITS. Instead of asking whether a chatbot can generally answer math questions, the authors ground the model in tutor context and student error data. That makes the article especially valuable for AIEDHK because it treats generative AI as a component inside a structured tutoring system rather than as a stand-alone teacher.

The paper examines three linked tasks. First, the LLM needs to diagnose student errors. Second, it needs to generate corrective feedback that responds to the specific error. Third, the system needs a way to assess whether the diagnosis and feedback are accurate and helpful. This workflow matters because feedback generation is one of the most tempting applications of LLMs in education. Teachers and tutor authors spend substantial time crafting hints, explanations, and bug-specific messages. If an LLM could reliably produce such feedback, it might reduce authoring burden and make tutoring systems more responsive to unusual learner responses.

The results are deliberately mixed. The study reports that GPT-4 can diagnose a range of student errors, but performance drops when responses are more complex or contain multiple problems. It also finds that generated feedback is often relevant and specific, yet a substantial share of hints are too general, incorrect, or reveal the answer. The authors also test whether an LLM can help evaluate generated feedback. That automated quality-control path is promising, but the reported helpfulness pass rate is low enough to show that autonomous feedback pipelines are not ready to be trusted without stronger review.

This makes the paper useful precisely because it resists a simple pro-AI or anti-AI conclusion. It shows that LLMs can add flexibility to ITS feedback, especially when they are given structured context from the tutor. At the same time, it documents the risk of misleading hints, overhelping, and weak automated evaluation. For research translation, the key point is that feedback quality is a safety issue. A fluent hint can still harm learning if it points to the wrong rule, masks a misconception, or gives away the solution before the learner has done the reasoning.

For AIEDHK, the article can become a practical checklist for LLM tutor design. A trustworthy system should specify the tutor context supplied to the model, the student error categories it can diagnose, the threshold for showing feedback, the human or automated review process, and the policy for withholding low-confidence hints. The paper also supports a hybrid design direction for Hong Kong products: combine the curriculum structure and learner modeling of ITS with the language flexibility of LLMs, while keeping teacher oversight and evidence-based quality checks visible. The strongest message is not that LLMs replace tutor authoring, but that they may extend it when embedded in a disciplined tutoring architecture.

관련 논문

A mathematics lecturer and peer discuss a university student's induction proof beside a laptop showing feedback on the next step.
학회 논문2026
학회 논문 206

LeanTutor: Towards a Verified AI Mathematical Proof Tutor

Manooshree Patel, Rayna Bhattacharyya, Thomas Lu, Arnav Mehta, Niels Voss, Narges Norouzi, Gireeja Ranade

Proceedings of the AAAI Conference on Artificial Intelligence

LeanTutor connects a language model to the Lean theorem prover to support mathematical proof feedback. Its technical evaluation shows promising hints on a small selected benchmark, but also exposes a crucial boundary: a verifier can check the formal proof only after the learner's words have been translated correctly. The study did not test classroom learning, and feedback evaluation excluded failed translations. It is an early system design with explicit limitations, not a validated replacement for mathematics instruction.

Mathematics EducationIntelligent TutoringFormal Verification
500단어 요약 읽기 →
Two pupils discuss an upward quadratic graph with a teacher beside a tablet offering calm mathematical hints.
저널 논문2025
저널 논문 204

Designing Safe and Relevant Generative Chats for Math Learning in Intelligent Tutoring Systems

Zachary Levonian, Owen Henkel, Chenglu Li, Millie-Ellen Postle

Journal of Educational Data Mining

More than 8,000 learners used a structured growth-mindset conversation inside a mathematics tutor, giving researchers a practical view of moderation and response quality. Monitoring found no overtly objectionable model outputs, but identified subtler failures to respond appropriately to concerning student messages. A separate study found that educators preferred moderately guided textbook-supported answers. Neither safety monitoring nor response preference establishes improved learning, and both findings depend on the particular system and evaluation context.

Intelligent TutoringMathematics EducationAI Safety
500단어 요약 읽기 →
Academic cover for a position paper on ChatGPT and large language models in education
리뷰2023
리뷰 02

ChatGPT for good? On opportunities and challenges of large language models for education

Enkelejda Kasneci, Kathrin Sessler, Stefan Kuechemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan Guennemann, Eyke Huellermeier, Stephan Krusche, Gitta Kutyniok, Tilman Michaeli, Claudia Nerdel, Juergen Pfeffer, Oleksandra Poquet, Michael Sailer, Albrecht Schmidt, Tina Seidel, Matthias Stadler, Jochen Weller, Jochen Kuehn, Gjergji Kasneci

Learning and Individual Differences

A widely cited position paper that balances the educational opportunities of large language models with risks around bias, privacy, assessment, and teacher guidance.

large language modelsChatGPTteacher support
500단어 요약 읽기 →