programming-education
Filtering by topic programming-education(3)Clear all filters
- PaperarXiv — AI in Education (cs.CY)17 Jul 2026
EduGuard: A Safe RAG-Based LLM Tutor for Programming Education
S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha, Jungpil Shin
EduGuard, a retrieval-augmented generation (RAG) tutoring framework for introductory programming, incorporates query understanding, instructor-approved retrieval, rubric-aware generation, claim verification, and overreliance control. Compared to baselines including GPT-4o-mini, EduGuard achieves higher correctness, grounding, and rubric alignment while reducing hallucination and direct-answer leakage. A pilot study showed improved learning outcomes and reduced overreliance, suggesting that safe GenAI tutoring requires explicit pedagogical control and evidence verification.
Original abstract
Generative AI (GenAI) is increasingly used by students for programming explanation, debugging, and assignment support. Yet unrestricted large language model (LLM) tutors can hallucinate, contradict course policy, reveal complete solutions, and foster passive dependence. This paper presents EduGuard, a safe retrieval-augmented generation (RAG) tutoring framework for introductory programming. EduGuard integrates query understanding, instructor-approved course retrieval, pedagogical strategy selection, rubric-aware generation, claim-level verification, and overreliance control. To make evaluation provenance explicit, we construct BILearn-CS, a 600-query instructor-authored, TA-validated benchmark spanning concept questions, debugging cases, misconceptions, assignment-support requests, code-mixed Bangla-English queries, and adversarial direct-answer prompts. Moving beyond a synthetic-only benchmark, we further evaluate on a 150-query public CS50-style course-forum set and run a small controlled pilot with 10 undergraduates using a counterbalanced pre-test/post-test design. Using Meta-Llama-3.1-8B-Instruct as the primary generator, hybrid FAISS/BM25 retrieval, and DeBERTa-v3-large-MNLI as an architecturally separate verifier, EduGuard is compared against strong baselines: GPT-4o-mini Tutor, Llama Socratic Tutor, LPITutor-style RAG, RAG with rubric prompting, and RAG with same-model self-checking. On BILearn-CS, EduGuard attains the best correctness (90.1%), grounding (89.4%), and rubric alignment (90.8%), with the lowest hallucination (4.9%) and direct-answer leakage (9.8%). In the pilot, it raises immediate post-test accuracy from 68.4% to 81.2% and cuts overreliance from 38.0% to 17.0% relative to GPT-4o-mini Tutor. These results suggest safe GenAI tutoring requires not only retrieval or strong prompting, but explicit pedagogical control, evidence verification, and deployment safeguards.
- PaperarXiv — AI in Education (cs.CY)13 Jul 2026
Programming Language Policy as an AI Literacy Equity Problem: A 15-Nation Comparative Analysis
Adrian-Marius Dumitran, Iulia-Maria Popescu
A 15-nation comparative analysis reveals structural challenges in secondary computer science education that undermine universal AI literacy: many students receive no programming exposure, and a 'Syntax Ceiling' concentrates advanced algorithmic depth (e.g., C++) in elite STEM tracks while most students only encounter Python. Governance structures, high-stakes exams, and shared teacher pipelines between general and specialist tracks are identified as key drivers. Achieving equitable AI literacy requires addressing access architectures and resource constraints beyond curriculum content.
Original abstract
The promise of AI literacy ``for all'' confronts a structural challenge embedded in how nations organise secondary computer science education. In most systems, a general-track subject -- Digital Literacy, ICT, TIC, or SNT -- bears the weight of universal AI literacy, while a specialist Informatics course serves STEM pathways separately. Yet the content and depth of the general track are shaped by governance decisions made largely with reference to the specialist one. This paper presents a comparative analysis of curricula and examination frameworks across fifteen countries, identifying two structural challenges. First, in several systems a significant portion of students completes secondary education without any formal programming exposure. Second, among those who do receive CS education, a \emph{Syntax Ceiling} emerges: Python-based instruction reaches most students, while the algorithmic depth associated with C++ remains concentrated in elite STEM tracks. Drawing on reform cases spanning centralised mandates (France, China, Japan), assessment-driven systems (Poland, Romania, South Korea), and recent universal reforms (Switzerland, Kazakhstan), we show that governance structures and high-stakes examinations are the primary drivers of both challenges -- and that specialist and general-track language choices are rarely independent, linked through shared teacher pipelines that curriculum policy seldom acknowledges. Achieving genuine AI literacy for all requires confronting not just curriculum content, but the access architectures and resource constraints that determine who receives it -- and at what depth.
- PaperarXiv — AI in Education (cs.CY)9 Jul 2026
From Execution to Education: A Bloom-Aligned Framework for Measuring Educational Control in LLMs
Yi Zhang, Julia Rayz
The paper introduces a Bloom-aligned framework to measure educational control in LLMs, defined as preserving instructional intent while adjusting cognitive demand. Applied to programming tasks, it finds that models reliably increase cognitive demand but struggle to lower it, revealing that strong execution performance does not guarantee Bloom-aligned educational control.
Original abstract
We introduce a Bloom-aligned framework for measuring educational control in Large Language Models (LLMs): the ability to preserve a task's instructional intent while shifting its cognitive demand toward specified learning objectives. We apply this framework to programming tasks in computer science education to study the gap between solving tasks and adapting them for learners. Using revised Bloom's Taxonomy as an operational scale of cognitive demand, we evaluate two intervention settings: general difficulty control, where models are asked to make tasks harder or easier, and Bloom's control, where models are asked to target higher or lower Bloom's levels. We evaluate a matched Qwen3-Next model pair, comparing Qwen3-Next-80B-A3B-Instruct with Qwen3-Coder-Next across 2,520 tasks from three benchmarks. The framework reveals a robust directional asymmetry: both models reliably increase cognitive demand, but struggle to lower it. We further characterize these outcomes with semantic-delta clustering and layer-wise Fisher's Discriminant Ratio probing. Within this controlled comparison, the general model shows clearer middle-layer separability for both general difficulty and Bloom-control contrasts, whereas the coder model shows weaker separability for general difficulty and a deeper peak for Bloom-control contrasts. These results show that strong execution performance does not automatically entail Bloom-aligned educational control.