35 views
# Scientific Articles on Generative AI in Education (2024-2025) This extraction summarizes the 7 articles found in the provided web page content that discuss generative AI in education and were published in 2024 or 2025. # Google Scholar Extracted Articles ### Article 1 - **Title:** A comprehensive review on generative AI for education - **Authors:** U Mittal, S Sai, V Chamola, D Sangwan - **Publication Date:** 2024 - **Abstract/Snippet:** … generative AI (GAI) and its potential applications within GAI, specifically mentioning generative … The article delves into the transformative impact of GAI in education, underscoring its … ### Article 2 - **Title:** Opportunities, challenges and school strategies for integrating generative AI in education - **Authors:** DTK Ng, EKC Chan, CK Lo - **Publication Date:** 2025 - **Abstract/Snippet:** … Generative Artificial Intelligence (GenAI) tools has led to their exploration and adoption in education … challenges associated with integrating GenAI in education, and the strategies that … ### Article 3 - **Title:** Generative AI in Education: Pedagogical, Theoretical, and Methodological Perspectives. - **Authors:** O Noroozi, S Soleimani, M Farrokhnia … - **Publication Date:** 2024 - **Abstract/Snippet:** … a powerful Generative Artificial Intelligence (GenAI) tool with the capacity to influence education. … of GenAI tools including ChatGPT in education, highlighting their potential to enhance … ### Article 4 - **Title:** The promise and challenges of generative AI in education - **Authors:** M Giannakos, R Azevedo, P Brusilovsky … - **Publication Date:** 2025 - **Abstract/Snippet:** … related to GenAI technologies in the context of education. In the commentary, it is … in education. Moreover, we highlight the danger of hastily adopting GenAI tools in education … ### Article 5 - **Title:** Generative AI in education and research: A systematic mapping review - **Authors:** A Yusuf, N Pervin, M Román‐González … - **Publication Date:** 2024 - **Abstract/Snippet:** … Given the potential applications of generative AI (GenAI) in education and its rising interest … and discussions on GenAI in K-12 education; a limited exploration of GenAI's impact using … ### Article 6 - **Title:** Ethical and regulatory challenges of Generative AI in education: a systematic review - **Authors:** IM García-López, L Trujillo-Liñán - **Publication Date:** 2025 - **Abstract/Snippet:** … benefits of GenAI or its overall impact on education, this work offers a comprehensive and … , and educational challenges of generative AI in education. Unlike earlier research that looked … ### Article 7 - **Title:** Critical analysis of the technological affordances, challenges and future directions of Generative AI in education: a systematic review - **Authors:** N Wang, X Wang, YS Su - **Publication Date:** 2024 - **Abstract/Snippet:** … hope for Generative AI’s role in assisting education, while … Based on deep learning models, Generative AI can ... # HAL - IA Générative en Éducation (2024-2025) ## Summary - **Total Articles Found**: 82 - **Year 2024**: 36 articles - **Year 2025**: 46 articles - **Selected for Report**: 20 most relevant articles - **Search Query**: IA générative éducation - **Date Range**: 2024-2025 - **Pages Processed**: 3 ## Top 20 Articles ### 1. Apprivoiser l’IA en enseignement postsecondaire : perspectives croisées des apprenants et apprenantes et du personnel enseignant au Nouveau-Brunswick - **Authors**: Florent Michelot , Alexandre Lepage - **Year**: 2025 - **HAL ID**: hal-05106379v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-05106379v1&title=Apprivoiser%20l%E2%80%99IA%20en%20enseignement%20postsecondaire%20%3A%20perspectives%20crois%C3%A9es%20des%20apprenants%20et%20apprenantes%20et%20du%20personnel%20enseignant%20au%20Nouveau-Brunswick - **Citation**: Revue internationale des technologies en pédagogie universitaire, 2025, 22 (1), ⟨10.18162/ritpu-2025-v22n1-12⟩ --- ### 2. Digital transformation: how to teach (with) generative AI in higher education? - **Authors**: Holly Many , Maria Shvetsova , Germain Forestier - **Year**: 2024 - **HAL ID**: hal-04690813v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fuha.hal.science%2Fhal-04690813v1&title=Digital%20transformation%3A%20how%20to%20teach%20(with)%20generative%20AI%20in%20higher%20education%3F - **Citation**: Études & Pédagogies, 2024, ⟨10.20870/eep.2024.8100⟩ --- ### 3. Usages pédagogiques de l'Intelligence artificielle et développement d'une posture critique - **Authors**: Aymeric Bouchereau - **Year**: 2024 - **HAL ID**: hal-04792950v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04792950v1&title=Usages%20p%C3%A9dagogiques%20de%20l%27Intelligence%20artificielle%20et%20d%C3%A9veloppement%20d%27une%20posture%20critique - **Citation**: Ticemed 14 Digitalisation des pratiques en éducation : risques, valeurs et opportunités, Oct 2024, Le Caire, Égypte --- ### 4. Une approche hybride de l'IA pour les technologies éducatives : augmenter les STI avec l'IA générative - **Authors**: Sofiya Kobylyanskaya , Catherine de Vulpillères , Pierre-Yves Oudeyer - **Year**: 2025 - **HAL ID**: hal-05329754v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Finria.hal.science%2Fhal-05329754v1&title=Une%20approche%20hybride%20de%20l%27IA%20pour%20les%20technologies%20%C3%A9ducatives%20%3A%20augmenter%20les%20STI%20avec%20l%27IA%20g%C3%A9n%C3%A9rative - **Citation**: 20e Conférence en Recherche d’Information et Applications (CORIA) 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 27ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL) Les 18e Rencontres Jeunes Chercheurs en RI (RJCRI), Jun 2025, Marseille, France. pp.145-148 --- ### 5. L'IA générative au service de la didactique de la grammaire : une approche réflexive en Master FLE - **Authors**: Paul Pouzergues - **Year**: 2025 - **HAL ID**: hal-04892924v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04892924v1&title=L%27IA%20g%C3%A9n%C3%A9rative%20au%20service%20de%20la%20didactique%20de%20la%20grammaire%20%3A%20une%20approche%20r%C3%A9flexive%20en%20Master%20FLE - **Citation**: NéALA 2025 Naturel et Artificiel en Linguistique Appliquée : une époque de paradoxes, Laboratoire ATILF, Jul 2025, Nancy, France --- ### 6. Éducation civique et citoyenneté en classe de FLE. Et si on essaye avec l’IA générative ? - **Authors**: Raffaele Romano - **Year**: 2025 - **HAL ID**: hal-04787184v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Famu.hal.science%2Fhal-04787184v1&title=%C3%89ducation%20civique%20et%20citoyennet%C3%A9%20en%20classe%20de%20FLE.%20Et%20si%20on%20essaye%20avec%20l%E2%80%99IA%20g%C3%A9n%C3%A9rative%20%3F - **Citation**: Le Français dans Le Monde, 2025, 456 --- ### 7. “Ménage à trois”: How does generative AI transform the teacherstudent relation in higher education? Perspectives in France and Japan - **Authors**: Luan Anh NGUYEN-TRAN , Isabelle Corbett-Etchevers - **Year**: 2024 - **HAL ID**: hal-04680611v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04680611v1&title=%E2%80%9CM%C3%A9nage%20%C3%A0%20trois%E2%80%9D%3A%20How%20does%20generative%20AI%20transform%20the%20teacherstudent%20relation%20in%20higher%20education%3F%20Perspectives%20in%20France%20and%20Japan - **Citation**: 29e Conférence de l’Association Information et Management, Association Information et Management, May 2024, Montpeliier, France --- ### 8. L’intelligence artificielle générative bouleverse-t-elle nos manières de s’informer, de veiller ou de s’exprimer ? Quelles perceptives pour l’éducation aux médias et à l’information ? - **Authors**: Pierre-Yves Connan - **Year**: 2025 - **HAL ID**: hal-05310524v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-05310524v1&title=L%E2%80%99intelligence%20artificielle%20g%C3%A9n%C3%A9rative%20bouleverse-t-elle%20nos%20mani%C3%A8res%20de%20s%E2%80%99informer%2C%20de%20veiller%20ou%20de%20s%E2%80%99exprimer%20%3F%20Quelles%20perceptives%20pour%20l%E2%80%99%C3%A9ducation%20aux%20m%C3%A9dias%20et%20%C3%A0%20l%E2%80%99information%20%3F - **Citation**: 2025 --- ### 9. Enseigner (avec) l'IA dans l'enseignement supérieur - **Authors**: Holly Many - **Year**: 2024 - **HAL ID**: hal-04577277v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fuha.hal.science%2Fhal-04577277v1&title=Enseigner%20(avec)%20l%27IA%20dans%20l%27enseignement%20sup%C3%A9rieur - **Citation**: Colloque international en éducation, CRIPFE, May 2024, Montreal (Canada), France --- ### 10. Artificial intelligence and Education - **Authors**: Elie Allouche - **Year**: 2024 - **HAL ID**: hal-04543937v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04543937v1&title=Artificial%20intelligence%20and%20Education - **Citation**: Ministère de l'éducation nationale. 2024, https://edunumrech.hypotheses.org/10764 --- ### 11. Désinformation visuelle et IA générative : quels enjeux pour l’éducation critique aux images ? - **Authors**: Florian Dauphin - **Year**: 2025 - **HAL ID**: hal-05110328v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fu-picardie.hal.science%2Fhal-05110328v1&title=D%C3%A9sinformation%20visuelle%20et%20IA%20g%C3%A9n%C3%A9rative%20%3A%20quels%20enjeux%20pour%20l%E2%80%99%C3%A9ducation%20critique%20aux%20images%20%3F - **Citation**: Former, informer, désinformer par l’image, Institut Français de Presse/CARISM, avec la collaboration du GRIPIC Programme de recherche européen DE FACTO (lutte contre la désinformation), Jun 2025, Paris ( France), France --- ### 12. Les Systèmes d'IA générative dans l'enseignement supérieur : des risques controversés et des scénarios contradictoires - **Authors**: Bernard Fallery , Florence Rodhain , Saloua Zgoulli-Swalhi - **Year**: 2024 - **HAL ID**: hal-04680468v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04680468v1&title=Les%20Syst%C3%A8mes%20d%27IA%20g%C3%A9n%C3%A9rative%20dans%20l%27enseignement%20sup%C3%A9rieur%20%3A%20des%20risques%20controvers%C3%A9s%20et%20des%20sc%C3%A9narios%20contradictoires - **Citation**: 29e Conférence de l’Association Information et Management, AIM 2024, May 2024, Montpelier, La Grende-Motte, France --- ### 13. Les SIC expliquées par ChatGPT. Une initiative pédagogique de littératie numérique et de réflexivité épistémique. - **Authors**: Alexandre Joux - **Year**: 2024 - **HAL ID**: hal-04933852v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04933852v1&title=Les%20SIC%20expliqu%C3%A9es%20par%20ChatGPT.%20Une%20initiative%20p%C3%A9dagogique%20de%20litt%C3%A9ratie%20num%C3%A9rique%20et%20de%20r%C3%A9flexivit%C3%A9%20%C3%A9pist%C3%A9mique. - **Citation**: Digitalisation des patiques en éducation : risques, valeurs et opportunités, TICEMED, Oct 2024, Le Caire (Egypt), Égypte --- ### 14. L'enseignement supérieur face aux progrès de l'IAG : des réponses institutionnelles en marche - **Authors**: Laurent Petit - **Year**: 2025 - **HAL ID**: hal-05347465v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-05347465v1&title=L%27enseignement%20sup%C3%A9rieur%20face%20aux%20progr%C3%A8s%20de%20l%27IAG%20%3A%20des%20r%C3%A9ponses%20institutionnelles%20en%20marche - **Citation**: Gilles Rouët. IA : enjeux et responsabilités, CNRS Editions, 2025, 978-2-271-15500-9 --- ### 15. Une régulation critique du Numérique et de l’IA en éducation - **Authors**: Jean-François Céci - **Year**: 2024 - **HAL ID**: hal-04782916v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-04782916v1&title=Une%20r%C3%A9gulation%20critique%20du%20Num%C3%A9rique%20et%20de%20l%E2%80%99IA%20en%20%C3%A9ducation - **Citation**: Pédagogie numérique et pratiques innovantes dans le système éducatif algérien - retour d’expériences Ouvrage collectif dans le cadre du projet PRFU, Fekra.com, p. 7-29, 2024, 978-9969-555-08-0 --- ### 16. Enseignement supérieur et Intelligence Artificielle : vers une pédagogie innovante de qualité (table ronde) - **Authors**: Thierry Gaillat - **Year**: 2025 - **HAL ID**: hal-05307934v1 - **URL**: - **Citation**: Carrefour de la recherche et de l'innovation pour l'amélioration de la qualité de l'enseignement supérieur à Madagascar, Jun 2025, Fianarantsoa, Madagascar --- ### 17. Intégrer l'IA générative dans la conception des évaluations - **Authors**: Camille Carton , Alexis Ghyselen - **Year**: 2024 - **HAL ID**: hal-05165710v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-05165710v1&title=Int%C3%A9grer%20l%27IA%20g%C3%A9n%C3%A9rative%20dans%20la%20conception%20des%20%C3%A9valuations - **Citation**: 2024 --- ### 18. Using customized GPT to develop prompting proficiency in architectural AI-generated images - **Authors**: Juan David Salazar Rodriguez , Sam Conrad Joyce , Julfendi Julfendi - **Year**: 2025 - **HAL ID**: hal-05037370v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-05037370v1&title=Using%20customized%20GPT%20to%20develop%20prompting%20proficiency%20in%20architectural%20AI-generated%20images - **Citation**: 2025 --- ### 19. Exploring the Uses and Non-Uses of Generative AI by MEEF Master's Students in Primary Teacher training - **Authors**: Jean-Luc Pierre Bergey , Damien Deias , Sara Mazziotti - **Year**: 2025 - **HAL ID**: hal-05156989v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Fhal.science%2Fhal-05156989v1&title=Exploring%20the%20Uses%20and%20Non-Uses%20of%20Generative%20AI%20by%20MEEF%20Master%27s%20Students%20in%20Primary%20Teacher%20training - **Citation**: NEALA 2025 : naturel et artificiel en linguistique appliquée. Une époque de paradoxe., Association Française de Linguistique Appliquée (Afla); Université de Lorraine, Jul 2025, Nancy, France --- ### 20. IA générative, société et éducation: En quoi l'IA générative représente-elle un enjeu dans la formation des citoyens ? - **Authors**: Pierre-Yves Oudeyer - **Year**: 2024 - **HAL ID**: hal-04945894v1 - **URL**: https://www.addtoany.com/share#url=https%3A%2F%2Finria.hal.science%2Fhal-04945894v1&title=IA%20g%C3%A9n%C3%A9rative%2C%20soci%C3%A9t%C3%A9%20et%20%C3%A9ducation%3A%20En%20quoi%20l%27IA%20g%C3%A9n%C3%A9rative%20repr%C3%A9sente-elle%20un%20enjeu%20dans%20la%20formation%20des%20citoyens%20%3F - **Citation**: Inria. 2024 --- # arXiv Generative AI in Education - Top 10 Articles (2024-2025) *Extracted on: 2025-11-16* --- ## 1. PustakAI: Curriculum-Aligned and Interactive Textbooks Using Large Language Models **Authors:** Shivam Sharma, Riya Naik, Tejas Gawas, Heramb Patil, Kunal Korgaonkar **Date:** Submitted 13 November, 2025; originally announced November 2025. **Abstract:** Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like content. This has revolutionized various sectors such as healthcare, software development, and education. In education, LLMs offer potential for personalized and interactive learning experiences, especially in regions with limited teaching resources. However, adapting these models effectively to curriculum-specific content, such as the National Council of Educational Research and Training (NCERT) syllabus in India, presents unique challenges in terms of accuracy, alignment, and pedagogical relevance. In this paper, we present the framework "PustakAI"\footnote{Pustak means `book' in many Indian languages.} for the design and evaluation of a novel question-answering dataset "NCERT-QA" aligned with the NCERT curriculum for English and Science subjects of grades 6 to 8. We classify the curated QA pairs as Factoid, Inferential, and Others (evaluative and reasoning). We evaluate the dataset with various prompting techniques, such as meta-prompt, few-shot, and CoT-style prompting, using diverse evaluation metrics to understand which approach aligns more efficiently with the structure and demands of the curriculum. Along with the usability of the dataset, we analyze the strengths and limitations of current open-source LLMs (Gemma3:1b, Llama3.2:3b, and Nemotron-mini:4b) and high-end LLMs (Llama-4-Scout-17B and Deepseek-r1-70B) as AI-based learning tools in formal education systems. △ Less --- ## 2. Owlgorithm: Supporting Self-Regulated Learning in Competitive Programming through LLM-Driven Reflection **Authors:** Juliana Nieto-Cardenas, Erin Joy Kramer, Peter Kurto, Ethan Dickey, Andres Bejarano **Date:** Submitted 13 November, 2025; originally announced November 2025. **Abstract:** We present Owlgorithm, an educational platform that supports Self-Regulated Learning (SRL) in competitive programming (CP) through AI-generated reflective questions. Leveraging GPT-4o, Owlgorithm produces context-aware, metacognitive prompts tailored to individual student submissions. Integrated into a second- and third-year CP course, the system-provided reflective prompts adapted to student outcomes: guiding deeper conceptual insight for correct solutions and structured debugging for partial or failed ones. Our exploratory assessment of student ratings and TA feedback revealed both promising benefits and notable limitations. While many found the generated questions useful for reflection and debugging, concerns were raised about feedback accuracy and classroom usability. These results suggest advantages of LLM-supported reflection for novice programmers, though refinements are needed to ensure reliability and pedagogical value for advanced learners. From our experience, several key insights emerged: GenAI can effectively support structured reflection, but careful prompt design, dynamic adaptation, and usability improvements are critical to realizing their potential in education. We offer specific recommendations for educators using similar tools and outline next steps to enhance Owlgorithm's educational impact. The underlying framework may also generalize to other reflective learning contexts. △ Less --- ## 3. SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations **Authors:** Eric Xie, Danielle Waterfield, Michael Kennedy, Aidong Zhang **Date:** Submitted 12 November, 2025; originally announced November 2025. **Abstract:** Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization. However, generating effective presentation slides introduces unique challenges due to the complexity of multimodal content creation and the need for precise, domain-specific information. Existing LLM-based solutions often fail to produce reliable and informative outputs, limiting their educational value. To address these limitations, we introduce SlideBot - a modular, multi-agent slide generation framework that integrates LLMs with retrieval, structured planning, and code generation. SlideBot is organized around three pillars: informativeness, ensuring deep and contextually grounded content; reliability, achieved by incorporating external sources through retrieval; and practicality, which enables customization and iterative feedback through instructor collaboration. It incorporates evidence-based instructional design principles from Cognitive Load Theory (CLT) and the Cognitive Theory of Multimedia Learning (CTML), using structured planning to manage intrinsic load and consistent visual macros to reduce extraneous load and enhance dual-channel learning. Within the system, specialized agents collaboratively retrieve information, summarize content, generate figures, and format slides using LaTeX, aligning outputs with instructor preferences through interactive refinement. Evaluations from domain experts and students in AI and biomedical education show that SlideBot consistently enhances conceptual accuracy, clarity, and instructional value. These findings demonstrate SlideBot's potential to streamline slide preparation while ensuring accuracy, relevance, and adaptability in higher education. △ Less --- ## 4. AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree Search **Authors:** Shuzhen Bi, Chang Song, Siyu Song, Jinze Lv, Jian Chen, Xinyun Wang, Aimin Zhou, Hao Hao **Date:** Submitted 12 November, 2025; originally announced November 2025. **Abstract:** Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data generation offers scalability, but its effectiveness relies on complex, multi-stage workflows, integrating prompt engineering and model orchestration. Existing automated workflow methods face a cold start problem: they require labeled datasets for reward modeling, which is especially problematic for subjective, open-ended tasks with no objective ground truth. We introduce AutoSynth, a framework that automates workflow discovery and optimization without reference datasets by reframing the problem as a Monte Carlo Tree Search guided by a novel dataset-free hybrid reward. This reward enables meta-learning through two LLM-as-judge components: one evaluates sample quality using dynamically generated task-specific metrics, and another assesses workflow code and prompt quality. Experiments on subjective educational tasks show that while expert-designed workflows achieve higher human preference rates (96-99% win rates vs. AutoSynth's 40-51%), models trained on AutoSynth-generated data dramatically outperform baselines (40-51% vs. 2-5%) and match or surpass expert workflows on certain metrics, suggesting discovery of quality dimensions beyond human intuition. These results are achieved while reducing human effort from 5-7 hours to just 30 minutes (>90% reduction). AutoSynth tackles the cold start issue in data-centric AI, offering a scalable, cost-effective method for subjective LLM tasks. Code: https://github.com/bisz9918-maker/AutoSynth. △ Less --- ## 5. VietMEAgent: Culturally-Aware Few-Shot Multimodal Explanation for Vietnamese Visual Question Answering **Authors:** Hai-Dang Nguyen, Minh-Anh Dang, Minh-Tan Le, Minh-Tuan Le **Date:** Submitted 12 November, 2025; originally announced November 2025. **Abstract:** Contemporary Visual Question Answering (VQA) systems remain constrained when confronted with culturally specific content, largely because cultural knowledge is under-represented in training corpora and the reasoning process is not rendered interpretable to end users. This paper introduces VietMEAgent, a multimodal explainable framework engineered for Vietnamese cultural understanding. The method integrates a cultural object detection backbone with a structured program generation layer, yielding a pipeline in which answer prediction and explanation are tightly coupled. A curated knowledge base of Vietnamese cultural entities serves as an explicit source of background information, while a dual-modality explanation module combines attention-based visual evidence with structured, human-readable textual rationales. We further construct a Vietnamese Cultural VQA dataset sourced from public repositories and use it to demonstrate the practicality of programming-based methodologies for cultural AI. The resulting system provides transparent explanations that disclose both the computational rationale and the underlying cultural context, supporting education and cultural preservation with an emphasis on interpretability and cultural sensitivity. △ Less --- ## 6. AI-generated podcasts: Synthetic Intimacy and Cultural Translation in NotebookLM's Audio Overviews **Authors:** Jill Walker Rettberg **Date:** Submitted 11 November, 2025; originally announced November 2025. **Abstract:** This paper analyses AI-generated podcasts produced by Google's NotebookLM, which generates audio podcasts with two chatty AI hosts discussing whichever documents a user uploads. While AI-generated podcasts have been discussed as tools, for instance in medical education, they have not yet been analysed as media. By uploading different types of text and analysing the generated outputs I show how the podcasts' structure is built around a fixed template. I also find that NotebookLM not only translates texts from other languages into a perky standardised Mid-Western American accent, it also translates cultural contexts to a white, educated, middle-class American default. This is a distinct development in how publics are shaped by media, marking a departure from the multiple public spheres that scholars have described in human podcasting from the early 2000s until today, where hosts spoke to specific communities and responded to listener comments, to an abstraction of the podcast genre. △ Less --- ## 7. Designing and Evaluating Malinowski's Lens: An AI-Native Educational Game for Ethnographic Learning **Authors:** Michael Hoffmann, Jophin John, Jan Fillies, Adrian Paschke **Date:** Submitted 10 November, 2025; originally announced November 2025. **Abstract:** This study introduces 'Malinowski's Lens', the first AI-native educational game for anthropology that transforms Bronislaw Malinowski's 'Argonauts of the Western Pacific' (1922) into an interactive learning experience. The system combines Retrieval-Augmented Generation with DALL-E 3 text-to-image generation, creating consistent VGA-style visuals as players embody Malinowski during his Trobriand Islands fieldwork (1915-1918). To address ethical concerns, indigenous peoples appear as silhouettes while Malinowski is detailed, prompting reflection on anthropological representation. Two validation studies confirmed effectiveness: Study 1 with 10 non-specialists showed strong learning outcomes (average quiz score 7.5/10) and excellent usability (SUS: 83/100). Study 2 with 4 expert anthropologists confirmed pedagogical value, with one senior researcher discovering "new aspects" of Malinowski's work through gameplay. The findings demonstrate that AI-driven educational games can effectively convey complex anthropological concepts while sparking disciplinary curiosity. This study advances AI-native educational game design and provides a replicable model for transforming academic texts into engaging interactive experiences. △ Less --- ## 8. Agentic Educational Content Generation for African Languages on Edge Devices **Authors:** Ravi Gupta, Guneet Bhatia **Date:** Submitted 1 November, 2025; originally announced November 2025. **Abstract:** Addressing educational inequity in Sub-Saharan Africa, this research presents an autonomous agent-orchestrated framework for decentralized, culturally adaptive educational content generation on edge devices. The system leverages four specialized agents that work together to generate contextually appropriate educational content. Experimental validation on platforms including Raspberry Pi 4B and NVIDIA Jetson Nano demonstrates significant performance achievements. InkubaLM on Jetson Nano achieved a Time-To-First-Token (TTFT) of 129 ms, an average inter-token latency of 33 ms, and a throughput of 45.2 tokens per second while consuming 8.4 W. On Raspberry Pi 4B, InkubaLM also led with 326 ms TTFT and 15.9 tokens per second at 5.8 W power consumption. The framework consistently delivered high multilingual quality, averaging a BLEU score of 0.688, cultural relevance of 4.4/5, and fluency of 4.2/5 across tested African languages. Through potential partnerships with active community organizations including African Youth & Community Organization (AYCO) and Florida Africa Foundation, this research aims to establish a practical foundation for accessible, localized, and sustainable AI-driven education in resource-constrained environments. Keeping focus on long-term viability and cultural appropriateness, it contributes to United Nations SDGs 4, 9, and 10. Index Terms - Multi-Agent Systems, Edge AI Computing, Educational Technology, African Languages, Rural Education, Sustainable Development, UN SDG. △ Less --- ## 9. EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers **Authors:** Yilin Jiang, Mingzi Zhang, Xuanyu Yin, Sheng Jin, Suyu Lu, Zuocan Ying, Zengyi Yu, Xiangjie Kong **Date:** Submitted 10 November, 2025; originally announced November 2025. **Abstract:** Large Language Models for Simulating Professions (SP-LLMs), particularly as teachers, are pivotal for personalized education. However, ensuring their professional competence and ethical safety is a critical challenge, as existing benchmarks fail to measure role-playing fidelity or address the unique teaching harms inherent in educational scenarios. To address this, we propose EduGuardBench, a dual-component benchmark. It assesses professional fidelity using a Role-playing Fidelity Score (RFS) while diagnosing harms specific to the teaching profession. It also probes safety vulnerabilities using persona-based adversarial prompts targeting both general harms and, particularly, academic misconduct, evaluated with metrics including Attack Success Rate (ASR) and a three-tier Refusal Quality assessment. Our extensive experiments on 14 leading models reveal a stark polarization in performance. While reasoning-oriented models generally show superior fidelity, incompetence remains the dominant failure mode across most models. The adversarial tests uncovered a counterintuitive scaling paradox, where mid-sized models can be the most vulnerable, challenging monotonic safety assumptions. Critically, we identified a powerful Educational Transformation Effect: the safest models excel at converting harmful requests into teachable moments by providing ideal Educational Refusals. This capacity is strongly negatively correlated with ASR, revealing a new dimension of advanced AI safety. EduGuardBench thus provides a reproducible framework that moves beyond siloed knowledge tests toward a holistic assessment of professional, ethical, and pedagogical alignment, uncovering complex dynamics essential for deploying trustworthy AI in education. See https://github.com/YL1N/EduGuardBench for Materials. △ Less --- ## 10. Understanding Student Interaction with AI-Powered Next-Step Hints: Strategies and Challenges **Authors:** Anastasiia Birillo, Aleksei Rostovskii, Yaroslav Golubev, Hieke Keuning **Date:** Submitted 9 November, 2025; originally announced November 2025. **Abstract:** Automated feedback generation plays a crucial role in enhancing personalized learning experiences in computer science education. Among different types of feedback, next-step hint feedback is particularly important, as it provides students with actionable steps to progress towards solving programming tasks. This study investigates how students interact with an AI-driven next-step hint system in an in-IDE learning environment. We gathered and analyzed a dataset from 34 students solving Kotlin tasks, containing detailed hint interaction logs. We applied process mining techniques and identified 16 common interaction scenarios. Semi-structured interviews with 6 students revealed strategies for managing unhelpful hints, such as adapting partial hints or modifying code to generate variations of the same hint. These findings, combined with our publicly available dataset, offer valuable opportunities for future research and provide key insights into student behavior, helping improve hint design for enhanced learning support. △ Less --- ## Extraction Metadata - **Total articles collected:** 150 - **Articles from 2024:** 0 - **Articles from 2025:** 150 - **Pages processed:** 3 - **Search query:** generative AI in education - **Source:** arXiv.org