Breadcrumb
- Home
- AI Hub For Education
- Research Study Repository
- Evidence Explorer
- AI Tools
- ChatGPT / OpenAI GPT
The Repository
Search and Filter
ChatGPT / OpenAI GPT
Studies tagged with AI from their full text or abstract; see each study for details.
Showing 571 - 600 of 1083 studies
Developing Strategies to Increase Capacity in AI Education
Noah Q. Cowit, Sri Yash Tadimalla, Stephanie T. Jones, Mary Lou Maher, Tracy Camp, Enrico Pontelli. (09/2025). arXiv.
A shortage of faculty with AI expertise and a lack of compensated time for training present major obstacles to expanding courses.
Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on Math Textbook
Eason Chen, Chuangji Li, Shizhuo Li, Zimo Xiao, Jionghao Lin, Kenneth R. Koedinger. (09/2025). arXiv.
Standard embedding-based retrieval outperformed GraphRAG, with the top model reaching 68.6% top-1 accuracy and 99.4% top-10 accuracy.
Affective Computing and Emotional Data: Challenges and Implications in Privacy Regulations, The AI Act, and Ethics in Large Language Models
Nicola Fabiano. (09/2025). arXiv.
Emotional data qualifies as personal data and may constitute special category data under the GDPR, imposing strict requirements on consent, purpose limitation, and data minimization.
Designing for Novice Debuggers: A Pilot Study on an Al-Assisted Debugging Tool
Oka Kurniawan, Erick Chandra, Christopher Michael POSKITT, Yannic Noller, Kenny Tsu Wei Choo, Cyrille Jegourel. (09/2025). arXiv.
Undergraduate participants gave the new tool an average System Usability Scale score of 75/100 and a satisfaction rating of 89/100, outperforming the previous version.
A Meta-Analysis Of LLM Effects On Students Across Qualification, Socialization, And Subjectification
Jiayu Huang, Ruoxin Ritter Wang, Jen-Hao Liu, Boming Xia, Yue Huang, Ruoxi Sun, Jason (Minhui) Xue, Jinan Zou. (09/2025). arXiv.
Large language models showed significant positive overall effects on qualification (g = 0.751), socialization (g = 0.745), and learner subjectification (g = 0.654), though subjectification was the least stable.
Enhancing Python Programming Education with an AI-Powered Code Helper: Design, Implementation, and Impact
Sayed Mahbub Hasan Amiri, Md Mainul Islam. (09/2025). arXiv.
The AI chatbot resolved 85% of errors across 1,500 student submissions, outperforming standalone GPT-4 (73%) and pylint (62%).
A Mega-Study Of Digital Twins Reveals Strengths, Weaknesses And Opportunities For Further Improvement
Tiany Peng, George Gui, Daniel J. Merlau, Grace Jiarui Fan, Malek Ben Sliman, Melanie Brucks, Eric J. Johnson, Vicki Morwitz, Abdullah Althenayyan, Silvia Bellezza, Dante Donati, Hortense Fong, Elizabeth Friedman, Ariana Guevara, Mohamed Hussein, Kinshuk Jerath, Bruce Kogut, Kristen Lane, Hannah Li, Patryk Perkowski, Oded Netzer, Olivier Toubia. (09/2025). arXiv.
Digital twins' answers were only modestly more accurate than generic base language models and correlated weakly with actual human choices (average correlation of 0.20).
AI Academy: Building Generative AI Literacy in Higher Ed Instructors
Si Chen, Xiuxiu Tang, Alison Cheng, Nitesh V Chawla, G. Alex Ambrose, Ronald Metoyer. (09/2025). arXiv.
Instructors showed significant self-assessed gains in six of nine generative AI literacy dimensions, including assessing outputs, prompt engineering, and tool use.
Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environments
Li Siyan, Zhen Xu, Vethavikashini Chithrra Raghuram, Xuanming Zhang, Renzhe Yu, Zhou Yu. (09/2025). arXiv.
Including peer forum context reduced simulated virtual teaching assistant performance, decreasing disciplinary understanding scores by 1 or 2 points in 59.7% of responses.
Generative AI alone may not be enough: Evaluating AI Support for Learning Mathematical Proof
Eason Chen, Sophia Judicke, Kayla Beigh, Xinyi Tang, Zimo Xiao, Chuangji Li, Shizhuo Li, Reed Luttmer, Shreya Singh, Maria Yampolsky, Naman Parikh, Yi Zhao, Meiyi Chen, Scarlett Huang, Anishka Mohanty, Gregory Johnson, John Mackey, Jionghao Lin, Kenneth R. Koedinger. (09/2025). arXiv.
Students with access to LLM-Tutor scored significantly higher on homework assignments (99.64%) than the control group (96.55%), but exam performance and study time showed no significant differences.
Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
Xiaoming Zhai. (09/2025). arXiv.
Researchers use six major approaches to generate concept maps: human-in-the-loop, weakly supervised learning, domain-specific fine-tuning, prompt engineering, hybrid knowledge base integration, and modular frameworks.
DeliverC: Teaching Pointers through GenAI-Powered Game-Based Learning
Wyatt Petula, Anushcka Joshi, Peggy Tu, Amrutha Somasundar, Suman Saha. (09/2025). arXiv.
Over 75% of surveyed students agreed that DeliverC supported confidence building, application, and metacognition, and 72% agreed it supported motivation.
Comparative Analysis of STEM and non-STEM Teachers' Needs for Integrating AI into Educational Environments
Bahare Riahi, Veronica Catete. (09/2025). arXiv.
Both STEM and non-STEM teachers wanted AI tools for plagiarism detection, adaptable rubrics, and detailed feedback, but non-STEM teachers uniquely emphasized evaluating creative, authentic work.
AI-driven formative assessment and adaptive learning in data-science education: Evaluating an LLM-powered virtual teaching assistant
Fadjimata Issoufou Anaroua, Qing Li, Yan Tang, Hong P.Liu. (09/2025). arXiv.
Embedding course context into chatbot prompts generated interactive Socratic dialogue that prompted deeper reflection compared to generic responses.
Perspectives and potential issues in using artificial intelligence for computer science education
Juho Vepsalainen, Petri Juntunen. (09/2025). arXiv.
AI-positive views highlight opportunities for personalized tutoring, rapid feedback, and automated assessments, while AI-critical perspectives warn of technology misuse, uncritical adoption, and pedagogical reductionism.
Participatory AI: A Scandinavian Approach to Human-Centered AI
Niklas Elmqvist, Eve Hoggan, Hans-Jorg Schulz, Marianne Graves Petersen, Peter Dalsgaard, Ira Assent, Olav Wedege Bertelsen, Akhil Arora, Kaj Gronbaek, Susanne Bodker, Clemens Nylandsted Klokmose, Rachel Charlotte Smith, Sebastian Hubenschmid, Christoph Albert Johns, Gabriela Molina Leon, Anton Wolter, Johannes Ellemose, Vaishali Dhanoa, Simon Aagaard Enni, Mille Skovhus Lunding, Karl-Emil Kjaer Bilstrup, Luke Connelly, Rafael Pablos Sarabia, Morten Birk, Juan Sanchez Esquivel, Joachim Nyborg, Stefanie Zollmann, Tobias Langlotz, Meredith Siang-Yun Chou, Jens Emil Sloth Gronbaek, Michael Wessely, Yijing Jiang, Caroline Berger, Duosi Dai, Michael Mose Biskjaer, German Leiva, Jonas Frich, Eva Eriksson, Kim Halskov, Thorbjorn Mikkelsen, Nearchos Potamitis, Michel Yildirim, Arvind Srinivasan, Jeanette Falk, Nanna Inie, Ole Sejer Iversen, Hugo Andersson. (09/2025). arXiv.
Early investments in participatory design reduced downstream project costs by mitigating costly misalignments, avoiding unwanted automation, and resolving conflicts with user expectations.
RAGs to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing
Timothy Rupprecht, Enfu Nan, Arash Akbari, Arman Akbari, Lei Lu, Priyanka Maana, Sean Duffy, Pu Zhao, Yumei He, David Kael, Yanzhi Wang. (09/2025). arXiv.
When challenged by hostile prompts, the proposed framework incorporated 35% more reference demonstration tokens into its responses than zero-shot and in-context learning baselines.
Exploring Conversational Design Choices in LLMs for Pedagogical Purposes: Socratic and Narrative Approaches for Improving Instructor's Teaching Practice
Si Chen, Isabel R. Molnar, Peiyu Li, Adam Acunin, Ting Hua, Alex Ambrose, Nitesh V Chawla, Ronald Metoyer. (09/2025). arXiv.
Instructors engaged more actively with the Socratic chatbot, contributing significantly more turns and words, while the Narrative chatbot generated much longer responses.
Prompting the Professoriate: A Qualitative Study of Instructor Perspectives on LLMs in Data Science Education*
Ana Elisa Lopez-Miranda, Tiffany Timbers, Rohan Alexander. (09/2025). arXiv.
Most instructors held pragmatic views toward language models, but 31 percent had not used them to teach and had no plans to do so.
Bridging Cultural Distance Between Models Default and Local Classroom Demands: How Global Teachers Adopt GenAI to Support Everyday Teaching Practices
Ruiwei Xiao, Qing Xiao, Xinying Hou, Hanqi Li, Phenyo Phemelo Moletsane, Hong Shen, John Stamper. (09/2025). arXiv.
Cultural distance operates across three levels: low distance requiring minor edits, mid distance needing sustained prompting and manual revision, and high distance presenting unbridgeable structural barriers.
Emerging Patterns of GenAI Use in K-12 Science and Mathematics Education
Lief Esbenshade, Shawon Sarkar, Drew Nucci, Ann Edwards, Sarah Nielsen, Joshua M. Rosenberg, Alex Liu, Zewei Tian, Min Sun, Zachary Zhang, Thomas Han, Yulia Lapicus, Kevin He. (09/2025). arXiv.
Over 50% of surveyed math and science teachers reported using generative AI tools, with 22% using them at least weekly.
Humanizing Automated Programming Feedback: Fine-Tuning Generative Models with Student-Written Feedback
Victor-Alexandru Padurean, Tung Phung, Nachiket Kotalwar, Michael Liut, Juho Leinonen, Paul Denny, Adish Singla. (09/2025). arXiv.
Fine-tuned Llama3-8B and Phi3-3.8B produced concise feedback that closely matched student communication style in length and variable mentions.
GenAI Voice Mode in Programming Education
Sven Jacobs, Natalie Kiesler. (09/2025). arXiv.
Nearly 29% of the AI's 416 feedback responses were incorrect, driven largely by persistent struggles with verbalizing programming code elements.
MusicScaffold: Bridging Machine Efficiency and Human Growth in Adolescent Creative Education through Generative AI
Zhejing Hu, Yan Liu, Zhi Zhang, Gong Chen, Bruce X.B. Yu, Junxian Li, Jiannong Cao. (09/2025). arXiv.
Students using MusicScaffold achieved higher prompt specificity (average score 3.00 versus 1.53 and 1.80) and incorporated significantly broader musical dimensions than control groups.
Aesthetic Experience and Educational Value in Co-creating Art with Generative AI: Evidence from a Survey of Young Learners
Chengyuan Zhang, Suzhe Xu. (09/2025). arXiv.
Most surveyed learners endorsed acting as the director while AI executes instructions (68.75%), but 62.50% reported that AI outputs often exceed expectations and feed back into their creativity.
Automated Classification of Tutors' Dialogue Acts Using Generative AI: A Case Study Using the CIMA Corpus
Liqun He, Jiaqi XU. (09/2025). arXiv.
GPT-4 achieved 80% accuracy, a weighted F1-score of 0.81, and a Cohen's Kappa of 0.74 when using combined instructions and two preceding dialogue turns.
YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models
Yaman Yu, Yiren Liu, Jacky Zhang, Yun Huang, Yang Wang. (09/2025). arXiv.
Existing safeguard models struggled to identify youth-specific safety risks, with binary detection F1 scores ranging from 0.09 for OpenAI Moderation API to 0.73 for Aegis.
Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities
Jarvis Haupt, Qin Lu, Yanning Shen, Jia Chen, Yue Dong, Dan McCreary, Mehmet Akcakaya, Georgios B. Giannakis. (09/2025). arXiv.
Large language models risk fabricating academic references and misrepresenting mathematical formulas, but grounding them through retrieval-augmented generation and structured knowledge graphs can reduce factual errors.
Feedback That Clicks: Introductory Physics Students' Valued Features in AI Feedback Generated From Self-Crafted and Engineered Prompts
Amogh Sirnoorkar, N. Sanjay Rebello. (09/2025). arXiv.
Students overwhelmingly preferred structured feedback, with 61.4% ranking feedback combining prompt engineering and effective feedback principles as most useful, while 61.2% ranked self-crafted prompt feedback as least useful.
Do Students Rely on AI? Analysis of Student-ChatGPT Conversations from a Field Study
Jiayu Zheng, Lingxin Hao, Kelun Lu, Ashi Garg, Mike Reese, Melo-Jean Yap, I-Jeng Wang, Xingyun Wu, Wenrui Huang, Jenna Hoffman, Ariane Kelly, My Le, Ryan Zhang, Yanyu Lin, Muhammad Faayez, Anqi Liu. (08/2025). arXiv.
Students followed AI recommendations in roughly 52% of interactions, but nearly half of those attempts ended in failed application where students followed correct AI guidance but answered incorrectly.
