Paul Denny

James Prather, Paul Denny, Juho Leinonen et al. · cmu

Recent advancements in artificial intelligence (AI) are fundamentally reshaping computing, with large language models (LLMs) now effectively being able to generate and interpret source code and natural language instructions. These emergent capabilities have sparked urgent questions in the computing education community around how educators should adapt their pedagogy to address the challenges and to leverage the opportunities presented by this new technology. In this working group report, we undertake a comprehensive exploration of LLMs in the context of computing education and make five significant contributions. First, we provide a detailed review of the literature on LLMs in computing education and synthesise findings from 71 primary articles. Second, we report the findings of a survey of computing students and instructors from across 20 countries, capturing prevailing attitudes towards LLMs and their use in computing education contexts. Third, to understand how pedagogy is already changing, we offer insights collected from in-depth interviews with 22 computing educators from five continents who have already adapted their curricula and assessments. Fourth, we use the ACM Code of Ethics to frame a discussion of ethical issues raised by the use of large language models in computing education, and we provide concrete advice for policy makers, educators, and students. Finally, we benchmark the performance of LLMs on various computing education datasets, and highlight the extent to which the capabilities of current models are rapidly improving. Our aim is that this report will serve as a focal point for both researchers and practitioners who are exploring, adapting, using, and evaluating LLMs and LLM-based tools in computing classrooms.

Charles Koutcheme, Nicola Dainese, Arto Hellas et al.

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.

Sami Sarsa, Paul Denny, Arto Hellas et al.

This article explores the natural language generation capabilities of large language models with application to the production of two types of learning resources common in programming courses. Using OpenAI Codex as the large language model, we create programming exercises (including sample solutions and test cases) and code explanations, assessing these qualitatively and quantitatively. Our results suggest that the majority of the automatically generated content is both novel and sensible, and in some cases ready to use as is. When creating exercises we find that it is remarkably easy to influence both the programming concepts and the contextual themes they contain, simply by supplying keywords as input to the model. Our analysis suggests that there is significant value in massive generative machine learning models as a tool for instructors, although there remains a need for some oversight to ensure the quality of the generated content before it is delivered to students. We further discuss the implications of OpenAI Codex and similar tools for introductory programming education and highlight future research streams that have the potential to improve the quality of the educational experience for both teachers and students alike.

Brett A. Becker, Paul Denny, James Finnie-Ansley et al.

The introductory programming sequence has been the focus of much research in computing education. The recent advent of several viable and freely-available AI-driven code generation tools present several immediate opportunities and challenges in this domain. In this position paper we argue that the community needs to act quickly in deciding what possible opportunities can and should be leveraged and how, while also working on how to overcome or otherwise mitigate the possible challenges. Assuming that the effectiveness and proliferation of these tools will continue to progress rapidly, without quick, deliberate, and concerted efforts, educators will lose advantage in helping shape what opportunities come to be, and what challenges will endure. With this paper we aim to seed this discussion within the computing education community.

Paul Denny, Viraj Kumar, Nasser Giacaman

GitHub Copilot is an artificial intelligence model for automatically generating source code from natural language problem descriptions. Since June 2022, Copilot has officially been available for free to all students as a plug-in to development environments like Visual Studio Code. Prior work exploring OpenAI Codex, the underlying model that powers Copilot, has shown it performs well on typical CS1 problems thus raising concerns about the impact it will have on how introductory programming courses are taught. However, little is known about the types of problems for which Copilot does not perform well, or about the natural language interactions that a student might have with Copilot when resolving errors. We explore these questions by evaluating the performance of Copilot on a publicly available dataset of 166 programming problems. We find that it successfully solves around half of these problems on its very first attempt, and that it solves 60\% of the remaining problems using only natural language changes to the problem description. We argue that this type of prompt engineering, which we believe will become a standard interaction between human and Copilot when it initially fails, is a potentially useful learning activity that promotes computational thinking skills, and is likely to change the nature of code writing skill development.

Paul Denny, James Prather, Brett A. Becker et al.

The computing education community has a rich history of pedagogical innovation designed to support students in introductory courses, and to support teachers in facilitating student learning. Very recent advances in artificial intelligence have resulted in code generation models that can produce source code from natural language problem descriptions -- with impressive accuracy in many cases. The wide availability of these models and their ease of use has raised concerns about potential impacts on many aspects of society, including the future of computing education. In this paper, we discuss the challenges and opportunities such models present to computing educators, with a focus on introductory programming classrooms. We summarize the results of two recent articles, the first evaluating the performance of code generation models on typical introductory-level programming problems, and the second exploring the quality and novelty of learning resources generated by these models. We consider likely impacts of such models upon pedagogical practice in the context of the most recent advances at the time of writing.

Juho Leinonen, Arto Hellas, Sami Sarsa et al.

A key part of learning to program is learning to understand programming error messages. They can be hard to interpret and identifying the cause of errors can be time-consuming. One factor in this challenge is that the messages are typically intended for an audience that already knows how to program, or even for programming environments that then use the information to highlight areas in code. Researchers have been working on making these errors more novice friendly since the 1960s, however progress has been slow. The present work contributes to this stream of research by using large language models to enhance programming error messages with explanations of the errors and suggestions on how to fix the error. Large language models can be used to create useful and novice-friendly enhancements to programming error messages that sometimes surpass the original programming error messages in interpretability and actionability. These results provide further evidence of the benefits of large language models for computing educators, highlighting their use in areas known to be challenging for students. We further discuss the benefits and downsides of large language models and highlight future streams of research for enhancing programming error messages.

James Prather, Brent N. Reeves, Paul Denny et al.

Recent developments in deep learning have resulted in code-generation models that produce source code from natural language and code-based prompts with high accuracy. This is likely to have profound effects in the classroom, where novices learning to code can now use free tools to automatically suggest solutions to programming exercises and assignments. However, little is currently known about how novices interact with these tools in practice. We present the first study that observes students at the introductory level using one such code auto-generating tool, Github Copilot, on a typical introductory programming (CS1) assignment. Through observations and interviews we explore student perceptions of the benefits and pitfalls of this technology for learning, present new observed interaction patterns, and discuss cognitive and metacognitive difficulties faced by students. We consider design implications of these findings, specifically in terms of how tools like Copilot can better support and scaffold the novice programming experience.

Jaromir Savelka, Paul Denny, Mark Liffiton et al. · cmu

The accurate classification of student help requests with respect to the type of help being sought can enable the tailoring of effective responses. Automatically classifying such requests is non-trivial, but large language models (LLMs) appear to offer an accessible, cost-effective solution. This study evaluates the performance of the GPT-3.5 and GPT-4 models for classifying help requests from students in an introductory programming class. In zero-shot trials, GPT-3.5 and GPT-4 exhibited comparable performance on most categories, while GPT-4 outperformed GPT-3.5 in classifying sub-categories for requests related to debugging. Fine-tuning the GPT-3.5 model improved its performance to such an extent that it approximated the accuracy and consistency across categories observed between two human raters. Overall, this study demonstrates the feasibility of using LLMs to enhance educational systems through the automated classification of student needs.

Juho Leinonen, Paul Denny, Stephen MacNeil et al.

Reasoning about code and explaining its purpose are fundamental skills for computer scientists. There has been extensive research in the field of computing education on the relationship between a student's ability to explain code and other skills such as writing and tracing code. In particular, the ability to describe at a high-level of abstraction how code will behave over all possible inputs correlates strongly with code writing skills. However, developing the expertise to comprehend and explain code accurately and succinctly is a challenge for many students. Existing pedagogical approaches that scaffold the ability to explain code, such as producing exemplar code explanations on demand, do not currently scale well to large classrooms. The recent emergence of powerful large language models (LLMs) may offer a solution. In this paper, we explore the potential of LLMs in generating explanations that can serve as examples to scaffold students' ability to understand and explain code. To evaluate LLM-created explanations, we compare them with explanations created by students in a large course ($n \approx 1000$) with respect to accuracy, understandability and length. We find that LLM-created explanations, which can be produced automatically on demand, are rated as being significantly easier to understand and more accurate summaries of code than student-created explanations. We discuss the significance of this finding, and suggest how such models can be incorporated into introductory programming education.

Yann Hicke, Anmol Agarwal, Qianou Ma et al.

Responding to the thousands of student questions on online QA platforms each semester has a considerable human cost, particularly in computing courses with rapidly growing enrollments. To address the challenges of scalable and intelligent question-answering (QA), we introduce an innovative solution that leverages open-source Large Language Models (LLMs) from the LLaMA-2 family to ensure data privacy. Our approach combines augmentation techniques such as retrieval augmented generation (RAG), supervised fine-tuning (SFT), and learning from human preferences data using Direct Preference Optimization (DPO). Through extensive experimentation on a Piazza dataset from an introductory CS course, comprising 10,000 QA pairs and 1,500 pairs of preference data, we demonstrate a significant 30% improvement in the quality of answers, with RAG being a particularly impactful addition. Our contributions include the development of a novel architecture for educational QA, extensive evaluations of LLM performance utilizing both human assessments and LLM-based metrics, and insights into the challenges and future directions of educational data processing. This work paves the way for the development of AI-TA, an intelligent QA assistant customizable for courses with an online QA platform

Paul Denny, Hassan Khosravi, Arto Hellas et al.

As an increasing number of students move to online learning platforms that deliver personalized learning experiences, there is a great need for the production of high-quality educational content. Large language models (LLMs) appear to offer a promising solution to the rapid creation of learning materials at scale, reducing the burden on instructors. In this study, we investigated the potential for LLMs to produce learning resources in an introductory programming context, by comparing the quality of the resources generated by an LLM with those created by students as part of a learnersourcing activity. Using a blind evaluation, students rated the correctness and helpfulness of resources generated by AI and their peers, after both were initially provided with identical exemplars. Our results show that the quality of AI-generated resources, as perceived by students, is equivalent to the quality of resources generated by their peers. This suggests that AI-generated resources may serve as viable supplementary material in certain contexts. Resources generated by LLMs tend to closely mirror the given exemplars, whereas student-generated resources exhibit greater variety in terms of content length and specific syntax features used. The study highlights the need for further research exploring different types of learning resources and a broader range of subject areas, and understanding the long-term impact of AI-generated resources on learning outcomes.

Hassan Khosravi, Dragan Gasevic, Shazia Sadiq et al.

Large language models (LLMs) are rapidly transforming knowledge work by improving the quality and efficiency of tasks such as writing, coding, and data analysis. However, their growing use in education has exposed a learning-performance paradox: while they can enhance short-term task performance, they may also undermine genuine learning, including cognitive growth, knowledge transfer, and metacognitive development. This paper addresses the question of how artificial intelligence should be designed and used to support learning rather than merely improve immediate outputs. We introduce the concept of AI learning companions, defined as adaptive, pedagogically informed, LLM-powered agents designed for integration into learning environments. We propose a framework for their design built on three interrelated foundations: a pedagogical foundation focused on how students learn with AI, an adaptive foundation focused on how AI learns about students, and a responsible design foundation ensuring systems remain transparent, accountable, inclusive, and secure. The framework is illustrated through five case studies spanning diverse educational contexts, levels, and tool designs, revealing both the promise and current limitations of existing tools. We conclude that there is a necessary shift away from LLMs designed for task-oriented performance, and beyond simply prompting them to act as tutors, toward deliberately developed AI learning companions that are pedagogically sound, adapt to their learners, and foster durable understanding, metacognitive growth, and learner agency.

Hassan Khosravi, Paul Denny, Steven Moore et al.

Engaging students in creating novel content, also referred to as learnersourcing, is increasingly recognised as an effective approach to promoting higher-order learning, deeply engaging students with course material and developing large repositories of content suitable for personalized learning. Despite these benefits, some common concerns and criticisms are associated with learnersourcing (e.g., the quality of resources created by students, challenges in incentivising engagement and lack of availability of reliable learnersourcing systems), which have limited its adoption. This paper presents a framework that considers the existing learnersourcing literature, the latest insights from the learning sciences and advances in AI to offer promising future directions for developing learnersourcing systems. The framework is designed around important questions and human-AI partnerships relating to four key aspects: (1) creating novel content, (2) evaluating the quality of the created content, (3) utilising learnersourced contributions of students and (4) enabling instructors to support students in the learnersourcing process. We then present two comprehensive case studies that illustrate the application of the proposed framework in relation to two existing popular learnersourcing systems.

Paul Denny, Juho Leinonen, James Prather et al.

With their remarkable ability to generate code, large language models (LLMs) are a transformative technology for computing education practice. They have created an urgent need for educators to rethink pedagogical approaches and teaching strategies for newly emerging skill sets. Traditional approaches to learning programming have focused on frequent and repeated practice at writing code. The ease with which code can now be generated has resulted in a shift in focus towards reading, understanding and evaluating LLM-generated code. In parallel with this shift, a new essential skill is emerging -- the ability to construct good prompts for code-generating models. This paper introduces a novel pedagogical concept known as a `Prompt Problem', designed to help students learn how to craft effective prompts for LLMs. A Prompt Problem challenges a student to create a natural language prompt that leads an LLM to produce the correct code for a specific problem. To support the delivery of Prompt Problems at scale, in this paper we also present a novel tool called Promptly which hosts a repository of Prompt Problems and automates the evaluation of prompt-generated code. We report empirical findings from a field study in which Promptly was deployed in a first-year Python programming course (n=54). We explore student interactions with the tool and their perceptions of the Prompt Problem concept. We found that Promptly was largely well-received by students for its ability to engage their computational thinking skills and expose them to new programming constructs. We also discuss avenues for future work, including variations on the design of Prompt Problems and the need to study their integration into the curriculum and teaching practice.

Qiming Bao, Juho Leinonen, Paul Denny et al.

Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the "alignment tax" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), Hybrid-DPO lifts NLI in four of five domains (+11.9% to +2.4x) with faster inference across all five, scaling down to compact base models without losing the alignment-tax mitigation. Our Qwen3-8B RLearner-LLM wins 95% of pairwise comparisons against its own SFT baseline; GPT-4o-mini in turn wins 95% against our concise output -- alongside the 69% win the same judge gives a verbose SFT over our DPO model, this replicates verbosity bias on a frontier comparator and motivates logic-aware metrics (NLI, ACR) over LLM-as-a-judge for knowledge-intensive generation.

Stephen MacNeil, Paul Denny, Andrew Tran et al.

Identifying and resolving logic errors can be one of the most frustrating challenges for novices programmers. Unlike syntax errors, for which a compiler or interpreter can issue a message, logic errors can be subtle. In certain conditions, buggy code may even exhibit correct behavior -- in other cases, the issue might be about how a problem statement has been interpreted. Such errors can be hard to spot when reading the code, and they can also at times be missed by automated tests. There is great educational potential in automatically detecting logic errors, especially when paired with suitable feedback for novices. Large language models (LLMs) have recently demonstrated surprising performance for a range of computing tasks, including generating and explaining code. These capabilities are closely linked to code syntax, which aligns with the next token prediction behavior of LLMs. On the other hand, logic errors relate to the runtime performance of code and thus may not be as well suited to analysis by LLMs. To explore this, we investigate the performance of two popular LLMs, GPT-3 and GPT-4, for detecting and providing a novice-friendly explanation of logic errors. We compare LLM performance with a large cohort of introductory computing students $(n=964)$ solving the same error detection task. Through a mixed-methods analysis of student and model responses, we observe significant improvement in logic error identification between the previous and current generation of LLMs, and find that both LLM generations significantly outperform students. We outline how such models could be integrated into computing education tools, and discuss their potential for supporting students when learning programming.

Lin Ni, Sijie Wang, Zeyu Zhang et al.

Learnersourcing offers great potential for scalable education through student content creation. However, predicting student performance on learnersourced questions, which is essential for personalizing the learning experience, is challenging due to the inherent noise in student-generated data. Moreover, while conventional graph-based methods can capture the complex network of student and question interactions, they often fall short under cold start conditions where limited student engagement with questions yields sparse data. To address both challenges, we introduce an innovative strategy that synergizes the potential of integrating Signed Graph Neural Networks (SGNNs) and Large Language Model (LLM) embeddings. Our methodology employs a signed bipartite graph to comprehensively model student answers, complemented by a contrastive learning framework that enhances noise resilience. Furthermore, LLM's contribution lies in generating foundational question embeddings, proving especially advantageous in addressing cold start scenarios characterized by limited graph data. Validation across five real-world datasets sourced from the PeerWise platform underscores our approach's effectiveness. Our method outperforms baselines, showcasing enhanced predictive accuracy and robustness.

Nicholas Gardella, James Prather, Juho Leinonen et al.

Code-generating Artificial Intelligence has gained popularity within both professional and educational programming settings over the past several years. While research and pedagogy are beginning to cope with this change, computing students are left to bear the unforeseen consequences of AI amidst a dearth of empirical evidence about its effects. Though pair programming between students is well studied and known to be beneficial to self-efficacy and academic achievement, it remains underutilized and further threatened by the proposition that AI can replace a human programming partner. In this paper, we present a controlled pair programming study with 22 participants who wrote Python code under time pressure in teams of two and individually with GitHub Copilot for 20 minutes each. They were incentivized by bonus compensation to balance performance with understanding and were retested individually on the programming tasks after a retention interval of one week. Subjective measures of workload and emotion as well as objective measures of performance and learning (retest performance) were collected. Results showed that participants performed significantly better with GitHub Copilot than their human teammate, and several dimensions of their workload were significantly reduced. However, the emotional effect of the human teammate was significantly more positive and arousing as compared to working with Copilot. Furthermore, there was a nonsignificant absolute retest performance reduction in the AI condition and a larger retest performance decrement in the AI condition. We recommend that educators strongly consider revisiting pair programming as an educational tool in addition to embracing modern AI.

Qiming Bao, Juho Leinonen, Alex Yuxuan Peng et al.

Large language models exhibit superior capabilities in processing and understanding language, yet their applications in educational contexts remain underexplored. Learnersourcing enhances learning by engaging students in creating their own educational content. When learnersourcing multiple-choice questions, creating explanations for the solution of a question is a crucial step; it helps other students understand the solution and promotes a deeper understanding of related concepts. However, it is often difficult for students to craft effective solution explanations, due to limited subject understanding. To help scaffold the task of automated explanation generation, we present and evaluate a framework called "ILearner-LLM", that iteratively enhances the generated explanations for the given questions with large language models. Comprising an explanation generation model and an explanation evaluation model, the framework generates high-quality student-aligned explanations by iteratively feeding the quality rating score from the evaluation model back into the instruction prompt of the explanation generation model. Experimental results demonstrate the effectiveness of our ILearner-LLM on LLaMA2-13B and GPT-4 to generate higher quality explanations that are closer to those written by students on five PeerWise datasets. Our findings represent a promising path to enrich the learnersourcing experience for students and to enhance the capabilities of large language models for educational applications.

Charles Koutcheme, Nicola Dainese, Sami Sarsa et al.

Large language models (LLMs) have shown great potential for the automatic generation of feedback in a wide range of computing contexts. However, concerns have been voiced around the privacy and ethical implications of sending student work to proprietary models. This has sparked considerable interest in the use of open source LLMs in education, but the quality of the feedback that such open models can produce remains understudied. This is a concern as providing flawed or misleading generated feedback could be detrimental to student learning. Inspired by recent work that has utilised very powerful LLMs, such as GPT-4, to evaluate the outputs produced by less powerful models, we conduct an automated analysis of the quality of the feedback produced by several open source models using a dataset from an introductory programming course. First, we investigate the viability of employing GPT-4 as an automated evaluator by comparing its evaluations with those of a human expert. We observe that GPT-4 demonstrates a bias toward positively rating feedback while exhibiting moderate agreement with human raters, showcasing its potential as a feedback evaluator. Second, we explore the quality of feedback generated by several leading open-source LLMs by using GPT-4 to evaluate the feedback. We find that some models offer competitive performance with popular proprietary LLMs, such as ChatGPT, indicating opportunities for their responsible use in educational settings.

Yan Cathy Hua, Paul Denny, Katerina Taskova et al.

Aspect-based sentiment analysis (ABSA) is a fine-grained type of sentiment analysis that identifies aspects and their associated opinions from a given text. With the surge of digital opinionated text data, ABSA gained increasing popularity for its ability to mine more detailed and targeted insights. Many review papers on ABSA subtasks and solution methodologies exist, however, few focus on trends over time or systemic issues relating to research application domains, datasets, and solution approaches. To fill the gap, this paper presents a systematic literature review (SLR) of ABSA studies with a focus on trends and high-level relationships among these fundamental components. This review is one of the largest SLRs on ABSA. To our knowledge, it is also the first to systematically examine the interrelations among ABSA research and data distribution across domains, as well as trends in solution paradigms and approaches. Our sample includes 727 primary studies screened from 8550 search results without time constraints via an innovative automatic filtering process. Our quantitative analysis not only identifies trends in nearly two decades of ABSA research development but also unveils a systemic lack of dataset and domain diversity as well as domain mismatch that may hinder the development of future ABSA research. We discuss these findings and their implications and propose suggestions for future research.

Yan Cathy Hua, Paul Denny, Jörg Wicker et al.

Every year, most educational institutions seek and receive an enormous volume of text feedback from students on courses, teaching, and overall experience. Yet, turning this raw feedback into useful insights is far from straightforward. It has been a long-standing challenge to adopt automatic opinion mining solutions for such education review text data due to the content complexity and low-granularity reporting requirements. Aspect-based Sentiment Analysis (ABSA) offers a promising solution with its rich, sub-sentence-level opinion mining capabilities. However, existing ABSA research and resources are very heavily focused on the commercial domain. In education, they are scarce and hard to develop due to limited public datasets and strict data protection. A high-quality, annotated dataset is urgently needed to advance research in this under-resourced area. In this work, we present EduRABSA (Education Review ABSA), the first public, annotated ABSA education review dataset that covers three review subject types (course, teaching staff, university) in the English language and all main ABSA tasks, including the under-explored implicit aspect and implicit opinion extraction. We also share ASQE-DPT (Data Processing Tool), an offline, lightweight, installation-free manual data annotation tool that generates labelled datasets for comprehensive ABSA tasks from a single-task annotation. Together, these resources contribute to the ABSA community and education domain by removing the dataset barrier, supporting research transparency and reproducibility, and enabling the creation and sharing of further resources. The dataset, annotation tool, and scripts and statistics for dataset processing and sampling are available at https://github.com/yhua219/edurabsa_dataset_and_annotation_tool.

Qiming Bao, Alex Yuxuan Peng, Zhenyun Deng et al.

Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering reliable data from the web to build comprehensive training datasets, subsequently affecting performance on downstream tasks. To address this, we introduce a novel logic-driven data augmentation approach, AMR-LDA. AMR-LDA converts the original text into an Abstract Meaning Representation (AMR) graph, a structured semantic representation that encapsulates the logical structure of the sentence, upon which operations are performed to generate logically modified AMR graphs. The modified AMR graphs are subsequently converted back into text to create augmented data. Notably, our methodology is architecture-agnostic and enhances both generative large language models, such as GPT-3.5 and GPT-4, through prompt augmentation, and discriminative large language models through contrastive learning with logic-driven data augmentation. Empirical evidence underscores the efficacy of our proposed method with improvement in performance across seven downstream tasks, such as reading comprehension requiring logical reasoning, textual entailment, and natural language inference. Furthermore, our method leads on the ReClor leaderboard at https://eval.ai/web/challenges/challenge-page/503/leaderboard/1347. The source code and data are publicly available at https://github.com/Strong-AI-Lab/Logical-Equivalence-driven-AMR-Data-Augmentation-for-Representation-Learning.

Yan Cathy Hua, Paul Denny, Jörg Wicker et al.

Aspect-based Sentiment Analysis (ABSA) is a fine-grained opinion mining approach that identifies and classifies opinions associated with specific entities (aspects) or their categories within a sentence. Despite its rapid growth and broad potential, ABSA research and resources remain concentrated in commercial domains, leaving analytical needs unmet in high-demand yet low-resource areas such as education and healthcare. Domain adaptation challenges and most existing methods' reliance on resource-intensive in-training knowledge injection further hinder progress in these areas. Moreover, traditional evaluation methods based on exact matches are overly rigid for ABSA tasks, penalising any boundary variations which may misrepresent the performance of generative models. This work addresses these gaps through three contributions: 1) We propose a novel evaluation method, Flexible Text Similarity Matching and Optimal Bipartite Pairing (FTS-OBP), which accommodates realistic extraction boundary variations while maintaining strong correlation with traditional metrics and offering fine-grained diagnostics. 2) We present the first ABSA study of small decoder-only generative language models (SLMs; <7B parameters), examining resource lower bounds via a case study in education review ABSA. We systematically explore data-free (in-context learning and weight merging) and data-light fine-tuning methods, and propose a multitask fine-tuning strategy that significantly enhances SLM performance, enabling 1.5-3.8 B models to surpass proprietary large models and approach benchmark results with only 200-1,000 examples on a single GPU. 3) We release the first public set of education review ABSA resources to support future research in low-resource domains.

Paul Denny, Sumit Gulwani, Neil T. Heffernan et al.

This survey article has grown out of the GAIED (pronounced "guide") workshop organized by the authors at the NeurIPS 2023 conference. We organized the GAIED workshop as part of a community-building effort to bring together researchers, educators, and practitioners to explore the potential of generative AI for enhancing education. This article aims to provide an overview of the workshop activities and highlight several future research directions in the area of GAIED.

Stanislav Pozdniakov, Jonathan Brazil, Solmaz Abdi et al.

Incorporating Generative AI (GenAI) and Large Language Models (LLMs) in education can enhance teaching efficiency and enrich student learning. Current LLM usage involves conversational user interfaces (CUIs) for tasks like generating materials or providing feedback. However, this presents challenges including the need for educator expertise in AI and CUIs, ethical concerns with high-stakes decisions, and privacy risks. CUIs also struggle with complex tasks. To address these, we propose transitioning from CUIs to user-friendly applications leveraging LLMs via API calls. We present a framework for ethically incorporating GenAI into educational tools and demonstrate its application in our tool, Feedback Copilot, which provides personalized feedback on student assignments. Our evaluation shows the effectiveness of this approach, with implications for GenAI researchers, educators, and technologists. This work charts a course for the future of GenAI in education.

Umar Alkafaween, Ibrahim Albluwi, Paul Denny

Automatically graded programming assignments provide instant feedback to students and significantly reduce manual grading time for instructors. However, creating comprehensive suites of test cases for programming problems within automatic graders can be time-consuming and complex. The effort needed to define test suites may deter some instructors from creating additional problems or lead to inadequate test coverage, potentially resulting in misleading feedback on student solutions. Such limitations may reduce student access to the well-documented benefits of timely feedback when learning programming. In this work, we evaluate the effectiveness of using Large Language Models (LLMs), as part of a larger workflow, to automatically generate test suites for CS1-level programming problems. Each problem's statement and reference solution are provided to GPT-4 to produce a test suite that can be used by an autograder. We evaluate our proposed approach using a sample of 26 problems, and more than 25,000 attempted solutions to those problems, submitted by students in an introductory programming course. We compare the performance of the LLM-generated test suites against the instructor-created test suites for each problem. Our findings reveal that LLM-generated test suites can correctly identify most valid solutions, and for most problems are at least as comprehensive as the instructor test suites. Additionally, the LLM-generated test suites exposed ambiguities in some problem statements, underscoring their potential to improve both autograding and instructional design.

Victor-Alexandru Pădurean, Paul Denny, Adish Singla

Debugging is an essential skill when learning to program, yet its instruction and emphasis often vary widely across introductory courses. In the era of code-generating large language models (LLMs), the ability for students to reason about code and identify errors is increasingly important. However, students frequently resort to trial-and-error methods to resolve bugs without fully understanding the underlying issues. Developing the ability to identify and hypothesize the cause of bugs is crucial but can be time-consuming to teach effectively through traditional means. This paper introduces BugSpotter, an innovative tool that leverages an LLM to generate buggy code from a problem description and verify the synthesized bugs via a test suite. Students interact with BugSpotter by designing failing test cases, where the buggy code's output differs from the expected result as defined by the problem specification. This not only provides opportunities for students to enhance their debugging skills, but also to practice reading and understanding problem specifications. We deployed BugSpotter in a large classroom setting and compared the debugging exercises it generated to exercises hand-crafted by an instructor for the same problems. We found that the LLM-generated exercises produced by BugSpotter varied in difficulty and were well-matched to the problem specifications. Importantly, the LLM-generated exercises were comparable to those manually created by instructors with respect to student performance, suggesting that BugSpotter could be an effective and efficient aid for learning debugging.

Meng Xia, Yan Chen, Qiao Jin et al.

This workshop addresses this gap by bringing together researchers and practitioners from AI, HCI, and the learning sciences to explore how interactive systems can better support learning. We focus on the design and evaluation of human-AI collaborative learning interfaces that are technically robust, human-centered, and pedagogically grounded. By fostering interdisciplinary dialogue, the workshop aims to identify shared challenges, design principles, and research directions for next-generation learning technologies.

James Prather, Brent N. Reeves, Paul Denny et al.

Non-native English speakers (NNES) face multiple barriers to learning programming. These barriers can be obvious, such as the fact that programming language syntax and instruction are often in English, or more subtle, such as being afraid to ask for help in a classroom full of native English speakers. However, these barriers are frustrating because many NNES students know more about programming than they can articulate in English. Advances in generative AI (GenAI) have the potential to break down these barriers because state of the art models can support interactions in multiple languages. Moreover, recent work has shown that GenAI can be highly accurate at code generation and explanation. In this paper, we provide the first exploration of NNES students prompting in their native languages (Arabic, Chinese, and Portuguese) to generate code to solve programming problems. Our results show that students are able to successfully use their native language to solve programming problems, but not without some difficulty specifying programming terminology and concepts. We discuss the challenges they faced, the implications for practice in the short term, and how this might transform computing education globally in the long term.

Charles Koutcheme, Nicola Dainese, Sami Sarsa et al.

The emergence of large language models (LLMs) has sparked enormous interest due to their potential application across a range of educational tasks. For example, recent work in programming education has used LLMs to generate learning resources, improve error messages, and provide feedback on code. However, one factor that limits progress within the field is that much of the research uses bespoke datasets and different evaluation metrics, making direct comparisons between results unreliable. Thus, there is a pressing need for standardization and benchmarks that facilitate the equitable comparison of competing approaches. One task where LLMs show great promise is program repair, which can be used to provide debugging support and next-step hints to students. In this article, we propose a novel educational program repair benchmark. We curate two high-quality publicly available programming datasets, present a unified evaluation procedure introducing a novel evaluation metric rouge@k for approximating the quality of repairs, and evaluate a set of five recent models to establish baseline performance.

Sebastian Gutierrez, Irene Hou, Jihye Lee et al.

Recent advancements in generative AI systems have raised concerns about academic integrity among educators. Beyond excelling at solving programming problems and text-based multiple-choice questions, recent research has also found that large multimodal models (LMMs) can solve Parsons problems based only on an image. However, such problems are still inherently text-based and rely on the capabilities of the models to convert the images of code blocks to their corresponding text. In this paper, we further investigate the capabilities of LMMs to solve graph and tree data structure problems based only on images. To achieve this, we computationally construct and evaluate a novel benchmark dataset comprising 9,072 samples of diverse graph and tree data structure tasks to assess the performance of the GPT-4o, GPT-4v, Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini 1.0 Pro Vision, and Claude 3 model families. GPT-4o and Gemini 1.5 Flash performed best on trees and graphs respectively. GPT-4o achieved 87.6% accuracy on tree samples, while Gemini 1.5 Flash, achieved 56.2% accuracy on graph samples. Our findings highlight the influence of structural and visual variations on model performance. This research not only introduces an LMM benchmark to facilitate replication and further exploration but also underscores the potential of LMMs in solving complex computing problems, with important implications for pedagogy and assessment practices.

Stephen MacNeil, Magdalena Rogalska, Juho Leinonen et al.

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.

Ali Alfageeh, Sadegh AlMahdi Kazemi Zarkouei, Daye Nam et al.

Background and Context. The increasing integration of large language models (LLMs) in computing education presents an emerging challenge in understanding how students use LLMs and craft prompts to solve computational tasks. Prior research has used both qualitative and quantitative methods to analyze prompting behavior, but these approaches lack scalability or fail to effectively capture the semantic evolution of prompts. Objective. In this paper, we investigate whether students prompts can be systematically analyzed using propositional logic constraints. We examine whether this approach can identify patterns in prompt evolution, detect struggling students, and provide insights into effective and ineffective strategies. Method. We introduce Prompt2Constraints, a novel method that translates students prompts into logical constraints. The constraints are able to represent the intent of the prompts in succinct and quantifiable ways. We used this approach to analyze a dataset of 1,872 prompts from 203 students solving introductory programming tasks. Findings. We find that while successful and unsuccessful attempts tend to use a similar number of constraints overall, when students fail, they often modify their prompts more significantly, shifting problem-solving strategies midway. We also identify points where specific interventions could be most helpful to students for refining their prompts. Implications. This work offers a new and scalable way to detect students who struggle in solving natural language programming tasks. This work could be extended to investigate more complex tasks and integrated into programming tools to provide real-time support.

Tony Haoran Feng, Paul Denny, Burkhard C. Wünsche et al.

CG (Computer Graphics) is a popular field of CS (Computer Science), but many students find this topic difficult due to it requiring a large number of skills, such as mathematics, programming, geometric reasoning, and creativity. Over the past few years, researchers have investigated ways to harness the power of GenAI (Generative Artificial Intelligence) to improve teaching. In CS, much of the research has focused on introductory computing. A recent study evaluating the performance of an LLM (Large Language Model), GPT-4 (text-only), on CG questions, indicated poor performance and reliance on detailed descriptions of image content, which often required considerable insight from the user to return reasonable results. So far, no studies have investigated the abilities of LMMs (Large Multimodal Models), or multimodal LLMs, to solve CG questions and how these abilities can be used to improve teaching. In this study, we construct two datasets of CG questions requiring varying degrees of visual perception skills and geometric reasoning skills, and evaluate the current state-of-the-art LMM, GPT-4o, on the two datasets. We find that although GPT-4o exhibits great potential in solving questions with visual information independently, major limitations still exist to the accuracy and quality of the generated results. We propose several novel approaches for CG educators to incorporate GenAI into CG teaching despite these limitations. We hope that our guidelines further encourage learning and engagement in CG classrooms.

Victor-Alexandru Pădurean, Paul Denny, Alkis Gotovos et al.

Computing students increasingly rely on generative AI tools for programming assistance, often without formal instruction or guidance. This highlights a need to teach students how to effectively interact with AI models, particularly through natural language prompts, to generate and critically evaluate code for solving computational tasks. To address this, we developed a novel platform for prompt programming that enables authentic dialogue-based interactions, supports problems involving multiple interdependent functions, and offers on-request execution of generated code. Data analysis from over 900 students in an introductory programming course revealed high engagement, with the majority of prompts occurring within multi-turn dialogues. Problems with multiple interdependent functions encouraged iterative refinement, with progression graphs highlighting several common strategies. Students were highly selective about the code they chose to test, suggesting that on-request execution of generated code promoted critical thinking. Given the growing importance of learning dialogue-based programming with AI, we provide this tool as a publicly accessible resource, accompanied by a corpus of programming problems for educational use.

Seth Bernstein, Paul Denny, Juho Leinonen et al.

Grasping complex computing concepts often poses a challenge for students who struggle to anchor these new ideas to familiar experiences and understandings. To help with this, a good analogy can bridge the gap between unfamiliar concepts and familiar ones, providing an engaging way to aid understanding. However, creating effective educational analogies is difficult even for experienced instructors. We investigate to what extent large language models (LLMs), specifically ChatGPT, can provide access to personally relevant analogies on demand. Focusing on recursion, a challenging threshold concept, we conducted an investigation analyzing the analogies generated by more than 350 first-year computing students. They were provided with a code snippet and tasked to generate their own recursion-based analogies using ChatGPT, optionally including personally relevant topics in their prompts. We observed a great deal of diversity in the analogies produced with student-prescribed topics, in contrast to the otherwise generic analogies, highlighting the value of student creativity when working with LLMs. Not only did students enjoy the activity and report an improved understanding of recursion, but they described more easily remembering analogies that were personally and culturally relevant.

Majeed Kazemitabaar, Runlong Ye, Xiaoning Wang et al.

Timely, personalized feedback is essential for students learning programming. LLM-powered tools like ChatGPT offer instant support, but reveal direct answers with code, which may hinder deep conceptual engagement. We developed CodeAid, an LLM-powered programming assistant delivering helpful, technically correct responses, without revealing code solutions. CodeAid answers conceptual questions, generates pseudo-code with line-by-line explanations, and annotates student's incorrect code with fix suggestions. We deployed CodeAid in a programming class of 700 students for a 12-week semester. A thematic analysis of 8,000 usages of CodeAid was performed, further enriched by weekly surveys, and 22 student interviews. We then interviewed eight programming educators to gain further insights. Our findings reveal four design considerations for future educational AI assistants: D1) exploiting AI's unique benefits; D2) simplifying query formulation while promoting cognitive engagement; D3) avoiding direct responses while encouraging motivated learning; and D4) maintaining transparency and control for students to asses and steer AI responses.

James Prather, Paul Denny, Juho Leinonen et al.

Large Language Models (LLMs) have upended decades of pedagogy in computing education. Students previously learned to code through \textit{writing} many small problems with less emphasis on code reading and comprehension. Recent research has shown that free code generation tools powered by LLMs can solve introductory programming problems presented in natural language with ease. In this paper, we propose a new way to teach programming with Prompt Problems. Students receive a problem visually, indicating how input should be transformed to output, and must translate that to a prompt for an LLM to decipher. The problem is considered correct when the code that is generated by the student prompt can pass all test cases. In this paper we present the design of this tool, discuss student interactions with it as they learn, and provide insights into this new class of programming problems as well as the design tools that integrate LLMs.

Lin Ni, Qiming Bao, Xiaoxuan Li et al.

Automated question quality rating (AQQR) aims to evaluate question quality through computational means, thereby addressing emerging challenges in online learnersourced question repositories. Existing methods for AQQR rely solely on explicitly-defined criteria such as readability and word count, while not fully utilising the power of state-of-the-art deep-learning techniques. We propose DeepQR, a novel neural-network model for AQQR that is trained using multiple-choice-question (MCQ) datasets collected from PeerWise, a widely-used learnersourcing platform. Along with designing DeepQR, we investigate models based on explicitly-defined features, or semantic features, or both. We also introduce a self-attention mechanism to capture semantic correlations between MCQ components, and a contrastive-learning approach to acquire question representations using quality ratings. Extensive experiments on datasets collected from eight university-level courses illustrate that DeepQR has superior performance over six comparative models.