arXiv subjects

Arto Hellas

Publications and source records attributed to Arto Hellas.

At least 19 recordsLinked to original sources

arXiv2026

Analyzing the Difficulty of Programming Assignments with Interpretable Knowledge Component Metrics

This research paper examines how Knowledge Components (KCs) - fine-grained concepts or skills required to solve programming tasks - can be used as interpretable signals for understanding assignment difficulty and student struggle in introductory programming courses. While prior work has focused on predictive models based on programming behavior, such models are often difficult to interpret and therefore hard to use for instructional decisions. We analyze KC-based metrics, including the number of KCs per assignment and changes in KC coverage between consecutive assignments. We examine correlations between the number of KCs and student performance on the assignment, and analyze changes in KCs across assignments to identify cases where performance declines without new concepts being introduced. Selected assignments are then qualitatively inspected to understand potential design issues. Our results on data from three introductory programming course datasets show that assignments involving more KCs are generally associated with lower performance, and that sudden shifts in required KCs can coincide with disruptions in learning progression. We also identify assignments where performance declines even though no new KCs are introduced, suggesting potential issues in task design or instruction, which could be examined with qualitative analysis. We propose an interpretable framework for analyzing programming assignments using KC-based metrics, with practical implications for instructors and course designers who want to better understand where and why students struggle, and how course materials might be improved. Our method can use KCs defined by an expert or extracted by an LLM, offering instructors an additional way to assess assignment quality beyond average correctness. It can be applied to any course with ordered assignments and measurable performance.

cs.CY↗

arXiv2026

The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance

When programming students encounter errors in their code, compiler messages or static analysis output often provide limited guidance, particularly for novice programmers. Personalized feedback from instructors can be effective but does not scale well. Recent advances in large language models (LLMs) enable automated feedback generation at scale. This study examines whether LLM-generated feedback with different levels of guidance is associated with differences in students' problem-solving behavior. We analyze effects on time to solution and number of attempts, and examine whether these effects differ by programming experience. We design three feedback types and compare them to a baseline in which students receive only compiler error messages. Results from an online programming course show that LLM-generated feedback is associated with faster time to solution compared to the no-feedback baseline, with less guided feedback showing slightly stronger effects. Overall, the findings suggest that feedback structure plays an important role in how students progress toward correct solutions and motivate further work on adaptive feedback designs and longer-term learning outcomes.

cs.HC↗

arXiv2026

Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education

Students learning algorithms often need support as they interpret traces, debug reasoning errors, and apply procedures across unfamiliar problem instances. In this paper, we present KITE (Knowledge-Informed Tutoring Engine), a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system designed to serve as a classroom teaching assistant for algorithmic reasoning and problem-solving tasks. KITE uses an intent-aware Socratic response strategy to tailor support to different student needs, responding with targeted hints, guiding questions, and progressive scaffolding intended to strengthen students' algorithmic problem-solving ability. To keep responses aligned with course content, KITE uses a multimodal RAG pipeline that retrieves relevant information from course materials. We evaluate KITE using three forms of assessment: RAGAs-based metrics for response grounding and quality, expert evaluation of pedagogical quality, and a simulated student pipeline in which a weaker language model interacts with KITE across two-turn dialogues and produces revised answers after receiving feedback. Results indicate that KITE produces contextually grounded and pedagogically appropriate responses. Further, using simulated students, KITE's feedback helped the student models produce more accurate follow-up responses on procedural and tracing questions, suggesting that its scaffolding can support algorithmic problem-solving. This work contributes a tutoring architecture and an evaluation approach for assessing retrieval-grounded explanations and scaffolded problem-solving feedback.

cs.AI↗

arXiv2026

AI-Generated Slides: Are They Good? Can Students Tell?

As generative AI (GenAI) tools become easily accessible, there is promise in using such tools to support instructors. To that end, this paper examines using GenAI to help generate slides from instructor authored course notes, emphasizing instructor and student perceptions. We examine an end-to-end education tool (NotebookLM), two general-purpose LLMs (Claude, M365 Copilot), and two coding assistants (Cursor, Claude Code). We first analyze whether GenAI generated slides are ``good'' via narrative assessment by educators. We choose the best slides to use (with some modification) in a real course setting, and compare the student perception of human vs. AI generated slides. We find that coding assistant tools produce slides that were most accurate, complete, and pedagogically sound. Additionally, students rate GenAI slides to be of similar quality as instructor-created slides, and cannot reliably identify which slides are AI-generated. Additionally, we find a negative correlation between a high quality rating and a high ``AI-generated'' rating, suggesting students associate poor quality with the source of the slides being AI. These findings highlight promising opportunities for integrating GenAI into instructional design workflows and call for further research on how educators can best harness such tools responsibly and effectively.

cs.AI↗

arXiv2026

The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness

Current Artificial Intelligence (AI)-based tutoring systems (AI tutors) are primarily evaluated based on the pedagogical quality of their feedback messages. While important, pedagogy alone is insufficient because it ignores a critical question: what do students actually do with the feedback they receive? We argue that AI tutor evaluation should be extended with a behavioral dimension grounded in student interaction data, which complements pedagogical assessment. We propose an evaluation framework and apply it to 10,235 code submissions with corresponding AI tutor feedback from an introductory undergraduate programming course to measure whether students act on tutor feedback and whether those actions are applied correctly. Using this framework to compare two deployed AI tutors across different semesters in a large-scale introductory computer science course reveals substantial differences in student engagement patterns that are not captured by pedagogy-only evaluation. Moreover, these engagement-based behavioral signals are more strongly associated with student perception of helpful feedback than pedagogical quality alone, providing a more complete and actionable picture of AI tutor performance.

cs.CY↗

arXiv2026

Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components

Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to students' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.

cs.HC↗

arXiv2026

Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation

Artificial students -- models that simulate how learners act and respond within educational systems -- are a promising tool for evaluating tutoring strategies and feedback mechanisms at scale. However, most existing approaches rely on prompting large, proprietary language models, limiting adaptability to specific courses and raising concerns around privacy, cost, and dependence. In this work, we propose a framework for training open-weight artificial programming learners directly from authentic student process data. Our approach serializes temporal log traces into a conversational format, representing each student's problem-solving process as a dialogue between the learner and their automated assessment system. Student code submissions and environment feedback, such as test outcomes, grades, and error traces, form alternating conversational turns, enabling models to learn from the iterative debugging process. We additionally introduce a training pipeline combining supervised fine-tuning with preference optimization to align models with authentic student debugging behavior. We evaluate our framework by training Qwen models at 4B and 8B scales on a large-scale dataset of real student submissions to Python programming assignments. Our results show that incorporating environment feedback strengthens models' ability to replicate student debugging behavior, improving over both prior code-only approaches and prompted large language models baselines in functional alignment and code similarity. We release our code to support reproducibility.

cs.AI↗

arXiv2026

When Looks Do Not Lie: Discourse Structure Guided In-Context Learning for Faithful Diagram Generation

GenAI is widespread in educational applications; however, it is known to generate content with intrinsic and extrinsic hallucination. We introduce a novel method for ICL diagram generation based on Rhetorical Structure Theory, which improves diagram faithfulness to its source text context. We find that ICL performance depends on task distribution and models' reasoning ability, with higher reasoning allowing better quality and performance for an out-of-distribution task. We perform an expert evaluation of 150 generated diagrams and analyze our findings using Bayesian GLMMs. Additionally, we use our evaluation rubric and samples from the data set for automated diagram evaluation, achieving statistically significant agreement with human evaluation.

cs.CL↗

arXiv2025

NEFMind: Parameter-Efficient Fine-Tuning of Open-Source LLMs for Telecom APIs Automation

The use of Service-Based Architecture in modern telecommunications has exponentially increased Network Functions (NFs) and Application Programming Interfaces (APIs), creating substantial operational complexities in service discovery and management. We introduce \textit{NEFMind}, a framework leveraging parameter-efficient fine-tuning of open-source Large Language Models (LLMs) to address these challenges. It integrates three core components: synthetic dataset generation from Network Exposure Function (NEF) API specifications, model optimization through Quantized-Low-Rank Adaptation, and performance evaluation via GPT-4 Ref Score and BertScore metrics. Targeting 5G Service-Based Architecture APIs, our approach achieves 85% reduction in communication overhead compared to manual discovery methods. Experimental validation using the open-source Phi-2 model demonstrates exceptional API call identification performance at 98-100% accuracy. The fine-tuned Phi-2 model delivers performance comparable to significantly larger models like GPT-4 while maintaining computational efficiency for telecommunications infrastructure deployment. These findings validate domain-specific, parameter-efficient LLM strategies for managing complex API ecosystems in next-generation telecommunications networks.

cs.NI↗

arXiv2025

How Large Language Models Are Changing MOOC Essay Answers: A Comparison of Pre- and Post-LLM Responses

The release of ChatGPT in late 2022 caused a flurry of activity and concern in the academic and educational communities. Some see the tool's ability to generate human-like text that passes at least cursory inspections for factual accuracy ``often enough'' a golden age of information retrieval and computer-assisted learning. Some, on the other hand, worry the tool may lead to unprecedented levels of academic dishonesty and cheating. In this work, we quantify some of the effects of the emergence of Large Language Models (LLMs) on online education by analyzing a multi-year dataset of student essay responses from a free university-level MOOC on AI ethics. Our dataset includes essays submitted both before and after ChatGPT's release. We find that the launch of ChatGPT coincided with significant changes in both the length and style of student essays, mirroring observations in other contexts such as academic publishing. We also observe -- as expected based on related public discourse -- changes in prevalence of key content words related to AI and LLMs, but not necessarily the general themes or topics discussed in the student essays as identified through (dynamic) topic modeling.

cs.CY↗

arXiv2025

Two Approaches for Programming Education in the Domain of Graphics: An Experiment

Context: Graphics is a popular domain for teaching introductory programming in a motivating way, even in text-based programming languages. Over the last few decades, a large number of libraries using different approaches have been developed for this purpose. Inquiry: Prior work in introductory programming that uses graphics as input and output has shown positive results in terms of engagement, but research is scarce on whether learners are able to use programming concepts learned through graphics for programming in other domains, transferring what they have learned. Approach: We conducted a randomized, controlled experiment with 145 students as participants divided into two groups. Both groups programmed using graphics in Python, but used different approaches: one group used a compositional graphics library named PyTamaro; the other used the Turtle graphics library from Python's standard library. Student engagement was assessed with surveys, and programming knowledge with a post-test on general programming concepts and programming tasks in the domain of graphics. Knowledge: We find few differences between the two groups on the post-test, despite the PyTamaro group having practiced on problems isomorphic to those in the post-test. The participants traced a compositional graphics program more accurately than a 'comparable' turtle graphics program. Both groups report high engagement and perceived learning; both perform well on simple program-writing tasks to create graphics. Grounding: Our findings are based on a controlled experiment with a count of 145 participants, which exceeds the sample size indicated by power analysis to detect a medium effect size. The complete instrument and teaching materials used in the study are available as appendixes. Importance: This study adds further evidence that graphics is an engaging domain for introductory programming; moreover, it shows that the compositional graphics approach adopted by PyTamaro yields engagement levels comparable to the venerable turtle approach. Compositional graphics code appears to be easier to trace than turtle graphics code. As for conceptual knowledge, our results indicate that practicing on programming tasks isomorphic to those of the test can still not be enough to achieve better transfer. This challenges programming educators and researchers to investigate further which graphics-based approaches work best and how to facilitate transfer.

cs.PL↗

arXiv2024

Overview of Web Application Performance Optimization Techniques

During its thirty years of existence, the World Wide Web has helped to transform the world and create digital economies. Although it started as a global information exchange, it has become the most significant available application platform on top of its initial target. One of the side effects of this evolution was perhaps suboptimal ways to deliver content over the web, leading to wasted resources and business through lost conversions. Technically speaking, there are many ways to improve the performance of web applications. In this article, we examine the currently available options and the latest trends related to improving web application performance.

cs.SE↗

arXiv2024

On the Opportunities of Large Language Models for Programming Process Data

Computing educators and researchers have used programming process data to understand how programs are constructed and what sorts of problems students struggle with. Although such data shows promise for using it for feedback, fully automated programming process feedback systems have still been an under-explored area. The recent emergence of large language models (LLMs) have yielded additional opportunities for researchers in a wide variety of fields. LLMs are efficient at transforming content from one format to another, leveraging the body of knowledge they have been trained with in the process. In this article, we discuss opportunities of using LLMs for analyzing programming process data. To complement our discussion, we outline a case study where we have leveraged LLMs for automatically summarizing the programming process and for creating formative feedback on the programming process. Overall, our discussion and findings highlight that the computing education research and practice community is again one step closer to automating formative programming process-focused feedback.

cs.CY↗

arXiv2024

LLM-itation is the Sincerest Form of Data: Generating Synthetic Buggy Code Submissions for Computing Education

There is a great need for data in computing education research. Data is needed to understand how students behave, to train models of student behavior to optimally support students, and to develop and validate new assessment tools and learning analytics techniques. However, relatively few computing education datasets are shared openly, often due to privacy regulations and issues in making sure the data is anonymous. Large language models (LLMs) offer a promising approach to create large-scale, privacy-preserving synthetic data, which can be used to explore various aspects of student learning, develop and test educational technologies, and support research in areas where collecting real student data may be challenging or impractical. This work explores generating synthetic buggy code submissions for introductory programming exercises using GPT-4o. We compare the distribution of test case failures between synthetic and real student data from two courses to analyze the accuracy of the synthetic data in mimicking real student data. Our findings suggest that LLMs can be used to generate synthetic incorrect submissions that are not significantly different from real student data with regard to test case failure distributions. Our research contributes to the development of reliable synthetic datasets for computing education research and teaching, potentially accelerating progress in the field while preserving student privacy.

cs.CY↗

arXiv2024

Comparing the Utility, Preference, and Performance of Course Material Search Functionality and Retrieval-Augmented Generation Large Language Model (RAG-LLM) AI Chatbots in Information-Seeking Tasks

Providing sufficient support for students requires substantial resources, especially considering the growing enrollment numbers. Students need help in a variety of tasks, ranging from information-seeking to requiring support with course assignments. To explore the utility of recent large language models (LLMs) as a support mechanism, we developed an LLM-powered AI chatbot that augments the answers that are produced with information from the course materials. To study the effect of the LLM-powered AI chatbot, we conducted a lab-based user study (N=14), in which the participants worked on tasks from a web software development course. The participants were divided into two groups, where one of the groups first had access to the chatbot and then to a more traditional search functionality, while another group started with the search functionality and was then given the chatbot. We assessed the participants' performance and perceptions towards the chatbot and the search functionality and explored their preferences towards the support functionalities. Our findings highlight that both support mechanisms are seen as useful and that support mechanisms work well for specific tasks, while less so for other tasks. We also observe that students tended to prefer the second support mechanism more, where students who were first given the chatbot tended to prefer the search functionality and vice versa.

cs.CY↗

arXiv2024

Synthetic Students: A Comparative Study of Bug Distribution Between Large Language Models and Computing Students

Large language models (LLMs) present an exciting opportunity for generating synthetic classroom data. Such data could include code containing a typical distribution of errors, simulated student behaviour to address the cold start problem when developing education tools, and synthetic user data when access to authentic data is restricted due to privacy reasons. In this research paper, we conduct a comparative study examining the distribution of bugs generated by LLMs in contrast to those produced by computing students. Leveraging data from two previous large-scale analyses of student-generated bugs, we investigate whether LLMs can be coaxed to exhibit bug patterns that are similar to authentic student bugs when prompted to inject errors into code. The results suggest that unguided, LLMs do not generate plausible error distributions, and many of the generated errors are unlikely to be generated by real students. However, with guidance including descriptions of common errors and typical frequencies, LLMs can be shepherded to generate realistic distributions of errors in synthetic code.

cs.CY↗

arXiv2024

Evaluating Language Models for Generating and Judging Programming Feedback

The emergence of large language models (LLMs) has transformed research and practice across a wide range of domains. Within the computing education research (CER) domain, LLMs have garnered significant attention, particularly in the context of learning programming. Much of the work on LLMs in CER, however, has focused on applying and evaluating proprietary models. In this article, we evaluate the efficiency of open-source LLMs in generating high-quality feedback for programming assignments and judging the quality of programming feedback, contrasting the results with proprietary models. Our evaluations on a dataset of students' submissions to introductory Python programming exercises suggest that state-of-the-art open-source LLMs are nearly on par with proprietary models in both generating and assessing programming feedback. Additionally, we demonstrate the efficiency of smaller LLMs in these tasks and highlight the wide range of LLMs accessible, even for free, to educators and practitioners.

cs.AI↗

arXiv2024

Evaluating Contextually Personalized Programming Exercises Created with Generative AI

Programming skills are typically developed through completing various hands-on exercises. Such programming problems can be contextualized to students' interests and cultural backgrounds. Prior research in educational psychology has demonstrated that context personalization of exercises stimulates learners' situational interests and positively affects their engagement. However, creating a varied and comprehensive set of programming exercises for students to practice on is a time-consuming and laborious task for computer science educators. Previous studies have shown that large language models can generate conceptually and contextually relevant programming exercises. Thus, they offer a possibility to automatically produce personalized programming problems to fit students' interests and needs. This article reports on a user study conducted in an elective introductory programming course that included contextually personalized programming exercises created with GPT-4. The quality of the exercises was evaluated by both the students and the authors. Additionally, this work investigated student attitudes towards the created exercises and their engagement with the system. The results demonstrate that the quality of exercises generated with GPT-4 was generally high. What is more, the course participants found them engaging and useful. This suggests that AI-generated programming problems can be a worthwhile addition to introductory programming courses, as they provide students with a practically unlimited pool of practice material tailored to their personal interests and educational needs.

cs.HC↗