Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models

Dominic Lohr H. Keuning Natalie Kiesler

31 Agustus 2023

Ever since the emergence of large language models (LLMs) and related applications, such as ChatGPT, its performance and error analysis for programming tasks have been subject to research. In this work-in-progress paper, we explore the potential of such LLMs for computing educators and learners, as we analyze the feedback it generates to a given input containing program code. In particular, we aim at (1) exploring how an LLM like ChatGPT responds to students seeking help with their introductory programming tasks, and (2) identifying feedback types in its responses. To achieve these goals, we used students' programming sequences from a dataset gathered within a CS1 course as input for ChatGPT along with questions required to elicit feedback and correct solutions. The results show that ChatGPT performs reasonably well for some of the introductory programming tasks and student errors, which means that students can potentially benefit. However, educators should provide guidance on how to use the provided feedback, as it can contain misleading information for novices.

Maciej Pankiewicz R. Baker

30 Juni 2023

Addressing the challenge of generating personalized feedback for programming assignments is demanding due to several factors, like the complexity of code syntax or different ways to correctly solve a task. In this experimental study, we automated the process of feedback generation by employing OpenAI’s GPT-3.5 model to generate personalized hints for students solving programming assignments on an automated assessment platform. Students rated the usefulness of GPT-generated hints positively. The experimental group (with GPT hints enabled) relied less on the platform's regular feedback but performed better in terms of percentage of successful submissions across consecutive attempts for tasks, where GPT hints were enabled. For tasks where the GPT feedback was made unavailable, the experimental group needed significantly less time to solve assignments. Furthermore, when GPT hints were unavailable, students in the experimental condition were initially less likely to solve the assignment correctly. This suggests potential over-reliance on GPT- generated feedback. However, students in the experimental condition were able to correct reasonably rapidly, reaching the same percentage correct after seven submission attempts. The availability of GPT hints did not significantly impact students' affective state.

Jaromír Šavelka Paul Denny Brad E. Sheese + 1 lainnya

14 Agustus 2023

Computing educators face significant challenges in providing timely support to students, especially in large class settings. Large language models (LLMs) have emerged recently and show great promise for providing on-demand help at a large scale, but there are concerns that students may over-rely on the outputs produced by these models. In this paper, we introduce CodeHelp, a novel LLM-powered tool designed with guardrails to provide on-demand assistance to programming students without directly revealing solutions. We detail the design of the tool, which incorporates a number of useful features for instructors, and elaborate on the pipeline of prompting strategies we use to ensure generated outputs are suitable for students. To evaluate CodeHelp, we deployed it in a first-year computer and data science course with 52 students and collected student interactions over a 12-week period. We examine students’ usage patterns and perceptions of the tool, and we report reflections from the course instructor and a series of recommendations for classroom use. Our findings suggest that CodeHelp is well-received by students who especially value its availability and help with resolving errors, and that for instructors it is easy to deploy and complements, rather than replaces, the support that they provide to students.

F. Hermans

1 Agustus 2020

One of the aspects of programming that learners often struggle with is the syntax of programming languages: remembering the right commands to use and combining those into a working program. Prior research demonstrated that students submit source code with syntax errors in 73% of cases and even the best students do so in 50% of cases. An analysis of 37 million compilations by 250.000 students found that the most common error was a syntax error, which occurred in almost 800.000 compilations. It was also found that Java and Perl are not easier to understand than a programming language with randomly generated keywords, stressing the difficulties that novices face in understanding syntax. This paper presents Hedy: a new way of teaching the syntax of a programming language to novices, inspired by educational methods by which punctuation is taught to children. Hedy starts as a simple programming language without any syntactic elements such as brackets, colons or indentation. The rules slowly and gradually change until the novices are programming in Python. Hedy is evaluated on 9714 programs.

Tongke Zhang Chunrong Fang Weisong Sun + 4 lainnya

13 Oktober 2023

Large Language Models (LLMs) have been gaining increasing attention and demonstrated promising performance across a variety of Software Engineering (SE) tasks, such as Automated Program Repair (APR), code summarization, and code completion. For example, ChatGPT, the latest black-box LLM, has been investigated by numerous recent research studies and has shown impressive performance in various tasks. However, there exists a potential risk of data leakage since these LLMs are usually close-sourced with unknown specific training details, e.g., pre-training datasets. In this paper, we seek to review the bug-fixing capabilities of ChatGPT on a clean APR benchmark with different research objectives. We first introduce {\benchmark}, a new benchmark with buggy and the corresponding fixed programs from competitive programming problems starting from 2023, after the training cutoff point of ChatGPT. The results on {\benchmark} show that ChatGPT is able to fix 109 out of 151 buggy programs using the basic prompt within 35 independent rounds, outperforming state-of-the-art LLMs CodeT5 and PLBART by 27.5\% and 62.4\% prediction accuracy. We also investigate the impact of three types of prompts, i.e., problem description, error feedback, and bug localization, leading to additional 34 fixed bugs. Besides, we provide additional discussion from the interactive nature of ChatGPT to illustrate the capacity of a dialog-based repair workflow with 9 additional fixed bugs. Inspired by the findings, we further pinpoint various challenges and opportunities for advanced SE study equipped with such LLMs (e.g.,~ChatGPT) in the near future. More importantly, our work calls for more research on the reevaluation of the achievements obtained by existing black-box LLMs across various SE tasks, not limited to ChatGPT on APR.