Stephen MacNeil

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.

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.

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.

Zijian Ding, Arvind Srinivasan, Stephen MacNeil et al.

Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofs-of concept of Large language Models' (LLMs) ability to generate cross-domain analogies. However, the reliability and potential usefulness of this capacity for augmenting human creative work has received little systematic exploration. In this paper, we systematically explore LLMs capacity to augment cross-domain analogical reasoning. Across three studies, we found: 1) LLM-generated cross-domain analogies were frequently judged as helpful in the context of a problem reformulation task (median 4 out of 5 helpfulness rating), and frequently (~80% of cases) led to observable changes in problem formulations, and 2) there was an upper bound of 25% of outputs bring rated as potentially harmful, with a majority due to potentially upsetting content, rather than biased or toxic content. These results demonstrate the potential utility -- and risks -- of LLMs for augmenting cross-domain analogical creativity.

Irene Hou, Owen Man, Sophie Mettille et al.

The advent of large language models is reshaping computing education. Recent research has demonstrated that these models can produce better explanations than students, answer multiple-choice questions at or above the class average, and generate code that can pass automated tests in introductory courses. These capabilities have prompted instructors to rapidly adapt their courses and assessment methods to accommodate changes in learning objectives and the potential for academic integrity violations. While some scholars have advocated for the integration of visual problems as a safeguard against the capabilities of language models, new multimodal language models now have vision and language capabilities that may allow them to analyze and solve visual problems. In this paper, we evaluate the performance of two large multimodal models on visual assignments, with a specific focus on Parsons problems presented across diverse visual representations. Our results show that GPT-4V solved 96.7\% of these visual problems, struggling minimally with a single Parsons problem. Conversely, Bard performed poorly by only solving 69.2\% of problems, struggling with common issues like hallucinations and refusals. These findings suggest that merely transitioning to visual programming problems might not be a panacea to issues of academic integrity in the generative AI era.

Cynthia Zastudil, Srishty Muthusekaran, Rayhona Nasimova et al.

Computing courses often feature active learning techniques that promote collaboration and social interaction between students. However, neurodivergent students' preferences and experiences with these techniques are not well understood. We conducted a survey of neurodivergent computing students (n=24), specifically autistic students or students with ADHD, and neurotypical computing students (n=20) to understand how the structure of collaborative active learning affects their comfort in computing courses. We also interviewed four computing students on the autism spectrum or with ADHD to gain more contextualized insights into their experiences and accessibility recommendations. Our survey surfaces how team dynamics and assignment structure can impact neurodivergent students' comfort in computing courses. Neurodivergent students expressed discomfort with assignments that lack structure or have ambiguous expectations. Neurodivergent students prefer smaller teams that work together frequently with explicitly defined roles. Our interviews identified ways that neurodivergent students cope with discomfort in collaborative active learning, including self-selecting roles and self-disclosure. While preliminary, our results highlight how instructors can design collaborative active learning to be more equitable and accessible for neurodivergent students.

James Prather, Juho Leinonen, Natalie Kiesler et al. · cmu

Generative AI (GenAI) is advancing rapidly, and the literature in computing education is expanding almost as quickly. Initial responses to GenAI tools were mixed between panic and utopian optimism. Many were fast to point out the opportunities and challenges of GenAI. Researchers reported that these new tools are capable of solving most introductory programming tasks and are causing disruptions throughout the curriculum. These tools can write and explain code, enhance error messages, create resources for instructors, and even provide feedback and help for students like a traditional teaching assistant. In 2024, new research started to emerge on the effects of GenAI usage in the computing classroom. These new data involve the use of GenAI to support classroom instruction at scale and to teach students how to code with GenAI. In support of the former, a new class of tools is emerging that can provide personalized feedback to students on their programming assignments or teach both programming and prompting skills at the same time. With the literature expanding so rapidly, this report aims to summarize and explain what is happening on the ground in computing classrooms. We provide a systematic literature review; a survey of educators and industry professionals; and interviews with educators using GenAI in their courses, educators studying GenAI, and researchers who create GenAI tools to support computing education. The triangulation of these methods and data sources expands the understanding of GenAI usage and perceptions at this critical moment for our community.

Lena Armstrong, Abbey Liu, Stephen MacNeil et al.

Large language models (LLMs) are increasingly being introduced in workplace settings, with the goals of improving efficiency and fairness. However, concerns have arisen regarding these models' potential to reflect or exacerbate social biases and stereotypes. This study explores the potential impact of LLMs on hiring practices. To do so, we conduct an AI audit of race and gender biases in one commonly-used LLM, OpenAI's GPT-3.5, taking inspiration from the history of traditional offline resume audits. We conduct two studies using names with varied race and gender connotations: resume assessment (Study 1) and resume generation (Study 2). In Study 1, we ask GPT to score resumes with 32 different names (4 names for each combination of the 2 gender and 4 racial groups) and two anonymous options across 10 occupations and 3 evaluation tasks (overall rating, willingness to interview, and hireability). We find that the model reflects some biases based on stereotypes. In Study 2, we prompt GPT to create resumes (10 for each name) for fictitious job candidates. When generating resumes, GPT reveals underlying biases; women's resumes had occupations with less experience, while Asian and Hispanic resumes had immigrant markers, such as non-native English and non-U.S. education and work experiences. Our findings contribute to a growing body of literature on LLM biases, particularly in workplace contexts.

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.

Irene Hou, Owen Man, Kate Hamilton et al.

The widespread adoption of generative AI is already impacting learning and help-seeking. While the benefits of generative AI are well-understood, recent studies have also raised concerns about increased potential for cheating and negative impacts on students' metacognition and critical thinking. However, the potential impacts on social interactions, peer learning, and classroom dynamics are not yet well understood. To investigate these aspects, we conducted 17 semi-structured interviews with undergraduate computing students across seven R1 universities in North America. Our findings suggest that help-seeking requests are now often mediated by generative AI. For example, students often redirected questions from their peers to generative AI instead of providing assistance themselves, undermining peer interaction. Students also reported feeling increasingly isolated and demotivated as the social support systems they rely on begin to break down. These findings are concerning given the important role that social interactions play in students' learning and sense of belonging.

Irene Hou, Hannah Vy Nguyen, Owen Man et al.

Help-seeking is a critical aspect of learning and problem-solving for computing students. Recent research has shown that many students are aware of generative AI (GenAI) tools; however, there are gaps in the extent and effectiveness of how students use them. With over two years of widespread GenAI usage, it is crucial to understand whether students' help-seeking behaviors with these tools have evolved and how. This paper presents findings from a repeated cross-sectional survey conducted among computing students across North American universities (n=95). Our results indicate shifts in GenAI usage patterns. In 2023, 34.1% of students (n=47) reported never using ChatGPT for help, ranking it fourth after online searches, peer support, and class forums. By 2024, this figure dropped sharply to 6.3% (n=48), with ChatGPT nearly matching online search as the most commonly used help resource. Despite this growing prevalence, there has been a decline in students' hourly and daily usage of GenAI tools, which may be attributed to a common tendency to underestimate usage frequency. These findings offer new insights into the evolving role of GenAI in computing education, highlighting its increasing acceptance and solidifying its position as a key help resource.

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.

Natalie Kiesler, Jacqueline Smith, Juho Leinonen et al.

Collaboration is a crucial part of computing education. The increase in AI capabilities over the last couple of years is bound to profoundly affect all aspects of systems and software engineering, including collaboration. In this position paper, we consider a scenario where AI agents would be able to take on any role in collaborative processes in computing education. We outline these roles, the activities and group dynamics that software development currently include, and discuss if and in what way AI could facilitate these roles and activities. The goal of our work is to envision and critically examine potential futures. We present scenarios suggesting how AI can be integrated into existing collaborations. These are contrasted by design fictions that help demonstrate the new possibilities and challenges for computing education in the AI era.

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.

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.