arXiv subjects

Paul Denny

Publications and source records attributed to Paul Denny.

At least 37 records · Page 2Linked to original sources

arXiv2025

Systematically Thinking about the Complexity of Code Structuring Exercises at Introductory Level

Decomposition and abstraction is an essential component of computational thinking, yet it is not always emphasized in introductory programming courses. In addition, as generative AI further reduces the focus on syntax and increases the importance of higher-level code reasoning, there is renewed opportunity to teach DA explicitly. In this paper, we introduce a framework for systematically assessing the complexity of code structuring tasks, where students must identify and separate meaningful abstractions within existing, unstructured code. The framework defines three dimensions of task complexity, each with multiple levels: repetition, code pattern, and data dependency. To support practical use, we provide example tasks mapped to these levels and offer an interactive tool for generating and exploring DA problems. The framework is designed to support the development of educational tasks that build students' skills with DA in the procedural paradigm.

cs.SE↗

arXiv2025

Data-Efficient Adaptation and a Novel Evaluation Method for Aspect-based Sentiment Analysis

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.

cs.CL↗

arXiv2025

Prompt Programming: A Platform for Dialogue-based Computational Problem Solving with Generative AI Models

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.

cs.CY↗

arXiv2025

Humanizing Automated Programming Feedback: Fine-Tuning Generative Models with Student-Written Feedback

The growing need for automated and personalized feedback in programming education has led to recent interest in leveraging generative AI for feedback generation. However, current approaches tend to rely on prompt engineering techniques in which predefined prompts guide the AI to generate feedback. This can result in rigid and constrained responses that fail to accommodate the diverse needs of students and do not reflect the style of human-written feedback from tutors or peers. In this study, we explore learnersourcing as a means to fine-tune language models for generating feedback that is more similar to that written by humans, particularly peer students. Specifically, we asked students to act in the flipped role of a tutor and write feedback on programs containing bugs. We collected approximately 1,900 instances of student-written feedback on multiple programming problems and buggy programs. To establish a baseline for comparison, we analyzed a sample of 300 instances based on correctness, length, and how the bugs are described. Using this data, we fine-tuned open-access generative models, specifically Llama3 and Phi3. Our findings indicate that fine-tuning models on learnersourced data not only produces feedback that better matches the style of feedback written by students, but also improves accuracy compared to feedback generated through prompt engineering alone, even though some student-written feedback is incorrect. This surprising finding highlights the potential of student-centered fine-tuning to improve automated feedback systems in programming education.

cs.CY↗

arXiv2025

Leveraging LLM Tutoring Systems for Non-Native English Speakers in Introductory CS Courses

Computer science has historically presented barriers for non-native English speaking (NNES) students, often due to language and terminology challenges. With the rise of large language models (LLMs), there is potential to leverage this technology to support NNES students more effectively. Recent implementations of LLMs as tutors in classrooms have shown promising results. In this study, we deployed an LLM tutor in an accelerated introductory computing course to evaluate its effectiveness specifically for NNES students. Key insights for LLM tutor use are as follows: NNES students signed up for the LLM tutor at a similar rate to native English speakers (NES); NNES students used the system at a lower rate than NES students -- to a small effect; NNES students asked significantly more questions in languages other than English compared to NES students, with many of the questions being multilingual by incorporating English programming keywords. Results for views of the LLM tutor are as follows: both NNES and NES students appreciated the LLM tutor for its accessibility, conversational style, and the guardrails put in place to guide users to answers rather than directly providing solutions; NNES students highlighted its approachability as they did not need to communicate in perfect English; NNES students rated help-seeking preferences of online resources higher than NES students; Many NNES students were unfamiliar with computing terminology in their native languages. These results suggest that LLM tutors can be a valuable resource for NNES students in computing, providing tailored support that enhances their learning experience and overcomes language barriers.

cs.HC↗

arXiv2025

From Prompts to Propositions: A Logic-Based Lens on Student-LLM Interactions

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.

cs.HC↗

arXiv2025

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning

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.

cs.CL↗

arXiv2025

Broadening Participation through Physical Computing: Replicating Sensor-Based Programming Workshops for Rural Students in Sri Lanka

In today's digital world, computing education offers critical opportunities, yet systemic inequities exclude under-represented communities, especially in rural, under-resourced regions. Early engagement is vital for building interest in computing careers and achieving equitable participation. Recent work has shown that the use of sensor-enabled tools and block-based programming can improve engagement and self-efficacy for students from under-represented groups, but these findings lack replication in diverse, resource-constrained settings. This study addresses this gap by implementing sensor-based programming workshops with rural students in Sri Lanka. Replicating methods from the literature, we conduct a between-group study (sensor vs. non-sensor) using Scratch and real-time environmental sensors. We found that students in both groups reported significantly higher confidence in programming in Scratch after the workshop. In addition, average changes in both self-efficacy and outcome expectancy were higher in the experimental (sensor) group than in the control (non-sensor) group, mirroring trends observed in the original study being replicated. We also found that using the sensors helped to enhance creativity and inspired some students to express an interest in information and communications technology (ICT) careers, supporting the value of such hands-on activities in building programming confidence among under-represented groups.

cs.CY↗

arXiv2025

Probing the Unknown: Exploring Student Interactions with Probeable Problems at Scale in Introductory Programming

Introductory programming courses often rely on small code-writing exercises that have clearly specified problem statements. This limits opportunities for students to practice how to clarify ambiguous requirements -- a critical skill in real-world programming. In addition, the emerging capabilities of large language models (LLMs) to produce code from well-defined specifications may harm student engagement with traditional programming exercises. This study explores the use of ``Probeable Problems'', automatically gradable tasks that have deliberately vague or incomplete specifications. Such problems require students to submit test inputs, or `probes', to clarify requirements before implementation. Through analysis of over 40,000 probes in an introductory course, we identify patterns linking probing behaviors to task success. Systematic strategies, such as thoroughly exploring expected behavior before coding, resulted in fewer incorrect code submissions and correlated with course success. Feedback from nearly 1,000 participants highlighted the challenges and real-world relevance of these tasks, as well as benefits to critical thinking and metacognitive skills. Probeable Problems are easy to set up and deploy at scale, and help students recognize and resolve uncertainties in programming problems.

cs.HC↗

arXiv2025

Exploring Student Behaviors and Motivations using AI TAs with Optional Guardrails

AI-powered chatbots and digital teaching assistants (AI TAs) are gaining popularity in programming education, offering students timely and personalized feedback. Despite their potential benefits, concerns about student over-reliance and academic misconduct have prompted the introduction of "guardrails" into AI TAs - features that provide scaffolded support rather than direct solutions. However, overly restrictive guardrails may lead students to bypass these tools and use unconstrained AI models, where interactions are not observable, thus limiting our understanding of students' help-seeking behaviors. To investigate this, we designed and deployed a novel AI TA tool with optional guardrails in one lab of a large introductory programming course. As students completed three code writing and debugging tasks, they had the option to receive guardrailed help or use a "See Solution" feature which disabled the guardrails and generated a verbatim response from the underlying model. We investigate students' motivations and use of this feature and examine the association between usage and their course performance. We found that 50% of the 885 students used the "See Solution" feature for at least one problem and 14% used it for all three problems. Additionally, low-performing students were more likely to use this feature and use it close to the deadline as they started assignments later. The predominant factors that motivated students to disable the guardrails were assistance in solving problems, time pressure, lack of self-regulation, and curiosity. Our work provides insights into students' solution-seeking motivations and behaviors, which has implications for the design of AI TAs that balance pedagogical goals with student preferences.

cs.HC↗

arXiv2025

ReDefining Code Comprehension: Function Naming as a Mechanism for Evaluating Code Comprehension

"Explain in Plain English" (EiPE) questions are widely used to assess code comprehension skills but are challenging to grade automatically. Recent approaches like Code Generation Based Grading (CGBG) leverage large language models (LLMs) to generate code from student explanations and validate its equivalence to the original code using unit tests. However, this approach does not differentiate between high-level, purpose-focused responses and low-level, implementation-focused ones, limiting its effectiveness in assessing comprehension level. We propose a modified approach where students generate function names, emphasizing the function's purpose over implementation details. We evaluate this method in an introductory programming course and analyze it using Item Response Theory (IRT) to understand its effectiveness as exam items and its alignment with traditional EiPE grading standards. We also publish this work as an open source Python package for autograding EiPE questions, providing a scalable solution for adoption.

cs.CY↗

arXiv2025

Counting the Trees in the Forest: Evaluating Prompt Segmentation for Classifying Code Comprehension Level

Reading and understanding code are fundamental skills for novice programmers, and especially important with the growing prevalence of AI-generated code and the need to evaluate its accuracy and reliability. ``Explain in Plain English'' questions are a widely used approach for assessing code comprehension, but providing automated feedback, particularly on comprehension levels, is a challenging task. This paper introduces a novel method for automatically assessing the comprehension level of responses to ``Explain in Plain English'' questions. Central to this is the ability to distinguish between two response types: multi-structural, where students describe the code line-by-line, and relational, where they explain the code's overall purpose. Using a Large Language Model (LLM) to segment both the student's description and the code, we aim to determine whether the student describes each line individually (many segments) or the code as a whole (fewer segments). We evaluate this approach's effectiveness by comparing segmentation results with human classifications, achieving substantial agreement. We conclude with how this approach, which we release as an open source Python package, could be used as a formative feedback mechanism.

cs.CY↗

arXiv2025

Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models

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.

cs.AI↗

arXiv2024

Breaking the Programming Language Barrier: Multilingual Prompting to Empower Non-Native English Learners

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.

cs.CY↗

arXiv2024

From Automation to Cognition: Redefining the Roles of Educators and Generative AI in Computing Education

Generative Artificial Intelligence (GenAI) offers numerous opportunities to revolutionise teaching and learning in Computing Education (CE). However, educators have expressed concerns that students may over-rely on GenAI and use these tools to generate solutions without engaging in the learning process. While substantial research has explored GenAI use in CE, and many Computer Science (CS) educators have expressed their opinions and suggestions on the subject, there remains little consensus on implementing curricula and assessment changes. In this paper, we describe our experiences with using GenAI in CS-focused educational settings and the changes we have implemented accordingly in our teaching in recent years since the popularisation of GenAI. From our experiences, we propose two primary actions for the CE community: 1) redesign take-home assignments to incorporate GenAI use and assess students on their process of using GenAI to solve a task rather than simply on the final product; 2) redefine the role of educators to emphasise metacognitive aspects of learning, such as critical thinking and self-evaluation. This paper presents and discusses these stances and outlines several practical methods to implement these strategies in CS classrooms. Then, we advocate for more research addressing the concrete impacts of GenAI on CE, especially those evaluating the validity and effectiveness of new teaching practices.

cs.CY↗

arXiv2024

Seeing the Forest and the Trees: Solving Visual Graph and Tree Based Data Structure Problems using Large Multimodal Models

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.

cs.AI↗

arXiv2024

Oversight in Action: Experiences with Instructor-Moderated LLM Responses in an Online Discussion Forum

The integration of large language models (LLMs) into computing education offers many potential benefits to student learning, and several novel pedagogical approaches have been reported in the literature. However LLMs also present challenges, one of the most commonly cited being that of student over-reliance. This challenge is compounded by the fact that LLMs are always available to provide instant help and solutions to students, which can undermine their ability to independently solve problems and diagnose and resolve errors. Providing instructor oversight of LLM-generated content can mitigate this problem, however it is often not practical in real-time learning contexts. Online class discussion forums, which are widely used in computing education, present an opportunity for exploring instructor oversight because they operate asynchronously. Unlike real-time interactions, the discussion forum format aligns with the expectation that responses may take time, making oversight not only feasible but also pedagogically appropriate. In this practitioner paper, we present the design, deployment, and evaluation of a `bot' module that is controlled by the instructor, and integrated into an online discussion forum. The bot assists the instructor by generating draft responses to student questions, which are reviewed, modified, and approved before release. Key features include the ability to leverage course materials, access archived discussions, and publish responses anonymously to encourage open participation. We report our experiences using this tool in a 12-week second-year software engineering course on object-oriented programming. Instructor feedback confirmed the tool successfully alleviated workload but highlighted a need for improvement in handling complex, context-dependent queries. We report the features that were viewed as most beneficial, and suggest avenues for future exploration.

cs.CY↗

arXiv2024

Howzat? Appealing to Expert Judgement for Evaluating Human and AI Next-Step Hints for Novice Programmers

Motivation: Students learning to program often reach states where they are stuck and can make no forward progress. An automatically generated next-step hint can help them make forward progress and support their learning. It is important to know what makes a good hint or a bad hint, and how to generate good hints automatically in novice programming tools, for example using Large Language Models (LLMs). Method and participants: We recruited 44 Java educators from around the world to participate in an online study. We used a set of real student code states as hint-generation scenarios. Participants used a technique known as comparative judgement to rank a set of candidate next-step Java hints, which were generated by Large Language Models (LLMs) and by five human experienced educators. Participants ranked the hints without being told how they were generated. Findings: We found that LLMs had considerable variation in generating high quality next-step hints for programming novices, with GPT-4 outperforming other models tested. When used with a well-designed prompt, GPT-4 outperformed human experts in generating pedagogically valuable hints. A multi-stage prompt was the most effective LLM prompt. We found that the two most important factors of a good hint were length (80--160 words being best), and reading level (US grade 9 or below being best). Offering alternative approaches to solving the problem was considered bad, and we found no effect of sentiment. Conclusions: Automatic generation of these hints is immediately viable, given that LLMs outperformed humans -- even when the students' task is unknown. The fact that only the best prompts achieve this outcome suggests that students on their own are unlikely to be able to produce the same benefit. The prompting task, therefore, should be embedded in an expert-designed tool.

cs.CY↗