An official website of the United States government
Code completion problems are an effective type of formative assessment; especially, when used to practice newly learned concepts or topics. While there is a growing body of research in computing education on the use of large language models (LLMs) to support learning content development, the use of LLMs for producing high-quality code completion problems has not yet been explored. In this paper, we analyze the capability of LLMs to generate effective distractors (i.e., plausible but incorrect options) and explanations for completion problems. We utilize common student misconceptions to improve the quality of the generated distractors. Our study suggests that LLMs are capable of generating reasonable distractors and explanations. At the same time, we identify a lack of a sufficiently granular taxonomy of common student misconceptions that would be needed for aligning the generated distractors with the common misconceptions and errors -- a gap that should be addressed in future work.
more »
« less
This content will become publicly available on March 3, 2026
Generating Effective Distractors for Introductory Programming Challenges: LLMs vs Humans
As large language models (LLMs) show great promise in generating a wide spectrum of educational materials, robust yet cost-effective assessment of the quality and effectiveness of such materials becomes an important challenge. Traditional approaches, including expert-based quality assessment and student-centered evaluation, are resource-consuming, and do not scale efficiently. In this work, we explored the use of pre-existing student learning data as a promising approach to evaluate LLM-generated learning materials. Specifically, we used a dataset where students were completing the program construction challenges by picking the correct answers among human-authored distractors to evaluate the quality of LLM-generated distractors for the same challenges. The dataset included responses from 1,071 students across 22 classes taught from Fall 2017 to Spring 2023. We evaluated five prominent LLMs (OpenAI-o1, GPT-4, GPT-4o, GPT-4o-mini, and Llama-3.1-8b) across three different prompts to see which combinations result in more effective distractors, i.e., those that are plausible (often picked by students), and potentially based on common misconceptions. Our results suggest that GPT-4o was the most effective model, matching close to 50% of the functional distractors originally authored by humans. At the same time, all of the evaluated LLMs generated many novel distractors, i.e., those that did not match the pre-existing human-authored ones. Our preliminary analysis shows that those appear to be promising. Establishing their effectiveness in real-world classroom settings is left for future work.
more »
« less
- Award ID(s):
- 2213789
- PAR ID:
- 10613695
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400707018
- Page Range / eLocation ID:
- 484 to 493
- Format(s):
- Medium: X
- Location:
- Dublin Ireland
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The burgeoning sophistication of Artificial Intelligence (AI) has catalyzed the rapid proliferation of Large Language Models (LLMs) within software development. These models are increasingly employed to automate the generation of functionally correct code, address complex computational problems, and facilitate the debugging of existing software systems. However, LLM-generated code often faces challenges due to inherent inefficiencies, including redundant logical structures, factually inconsistent content (hallucinations), and programming errors. To address this issue, our research rigorously evaluated the computational efficiency of Python code generated by three prominent LLMs: GPT-4o-Mini, GPT-3.5-Turbo, and GPT-4-Turbo. The evaluation metrics encompass execution time, memory utilization, and peak memory consumption, while maintaining the functional correctness of the generated code. Leveraging the EffiBench benchmark datasets within the Google Vertex AI Workbench environment, across a spectrum of machine configurations, the study implemented a consistent seed parameter to ensure experimental reproducibility. Furthermore, we investigated the impact of two distinct optimization strategies: Chain-of-Thought (CoT) prompting and model fine-tuning. Our findings reveal a significant enhancement in efficiency metrics for GPT-4o-Mini and GPT-3.5-Turbo when employing CoT prompting; however, this trend was not observed for GPT-4-Turbo. Based on its promising performance with CoT prompting, we selected the GPT-4o-Mini model for subsequent fine-tuning, aiming to further enhance both its computational efficiency and accuracy. However, contrary to our expectations, fine-tuning the GPT-4o-Mini model led to a discernible degradation in both its accuracy and computational efficiency. In conclusion, this study provides empirical evidence suggesting that the deployment of high-CPU machine configurations, in synergy with the utilization of the GPT-4o-Mini model and CoT prompting techniques, yields demonstrably more efficient and accurate LLM-generated Python code, particularly within computationally intensive application scenarios.more » « less
-
Exposing students to low-quality assessments such as multiple-choice questions (MCQs) and short answer questions (SAQs) is detrimental to their learning, making it essential to accurately evaluate these assessments. Existing evaluation methods are often challenging to scale and fail to consider their pedagogical value within course materials. Online crowds offer a scalable and cost-effective source of intelligence, but often lack necessary domain expertise. Advancements in Large Language Models (LLMs) offer automation and scalability, but may also lack precise domain knowledge. To explore these trade-offs, we compare the effectiveness and reliability of crowdsourced and LLM-based methods for assessing the quality of 30 MCQs and SAQs across six educational domains using two standardized evaluation rubrics. We analyzed the performance of 84 crowdworkers from Amazon's Mechanical Turk and Prolific, comparing their quality evaluations to those made by the three LLMs: GPT-4, Gemini 1.5 Pro, and Claude 3 Opus. We found that crowdworkers on Prolific consistently delivered the highest-quality assessments, and GPT-4 emerged as the most effective LLM for this task. Our study reveals that while traditional crowdsourced methods often yield more accurate assessments, LLMs can match this accuracy in specific evaluative criteria. These results provide evidence for a hybrid approach to educational content evaluation, integrating the scalability of AI with the nuanced judgment of humans. We offer feasibility considerations in using AI to supplement human judgment in educational assessment.more » « less
-
Thematic Analysis (TA) is a fundamental method in healthcare research for analyzing transcript data, but it is resource-intensive and difficult to scale for large, complex datasets. This study investigates the potential of large language models (LLMs) to augment the inductive TA process in high-stakes healthcare settings. Focusing on interview transcripts from parents of children with Anomalous Aortic Origin of a Coronary Artery (AAOCA), a rare congenital heart disease, we propose an LLM-Enhanced Thematic Analysis (LLM-TA) pipeline. Our pipeline integrates an affordable state-of-the-art LLM (GPT-4o mini), LangChain, and prompt engineering with chunking techniques to analyze nine detailed transcripts following the inductive TA framework. We evaluate the LLM-generated themes against human-generated results using thematic similarity metrics, LLM-assisted assessments, and expert reviews. Results demonstrate that our pipeline outperforms existing LLM-assisted TA methods significantly. While the pipeline alone has not yet reached human-level quality in inductive TA, it shows great potential to improve scalability, efficiency, and accuracy while reducing analyst workload when working collaboratively with domain experts. We provide practical recommendations for incorporating LLMs into high-stakes TA workflows and emphasize the importance of close collaboration with domain experts to address challenges related to real-world applicability and dataset complexity.more » « less
-
Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. For programming tasks, most models are finetuned with costly human-annotated instruction-response pairs or those generated by large, proprietary LLMs, which may not be permitted. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for self-aligning code LLMs without extensive human annotations or distillation. SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks. It then samples multiple responses per task, pairs each with test cases, and validates them in a sandbox environment. Finally, passing examples are selected for instruction tuning. In our primary experiments, we use SelfCodeAlign with CodeQwen1.5-7B to generate a dataset of 74k instruction-response pairs. Finetuning on this dataset leads to a model that achieves a 67.1 pass@1 on HumanEval+, surpassing CodeLlama-70B-Instruct despite being ten times smaller. Across all benchmarks, this finetuned model consistently outperforms the original version trained with OctoPack, the previous state-of-the-art method for instruction tuning without human annotations or distillation. Additionally, we show that SelfCodeAlign is effective across LLMs of various sizes, from 3B to 33B, and that the base models can benefit more from alignment with their own data distribution. We further validate each component’s effectiveness in our pipeline, showing that SelfCodeAlign outperforms both direct distillation from GPT-4o and leading GPT-3.5-based distillation methods, such as OSS-Instruct and Evol-Instruct. SelfCodeAlign has also led to the creation of StarCoder2-Instruct, the first fully transparent, permissively licensed, and self-aligned code LLM that achieves state-of-the-art coding performance. Overall, SelfCodeAlign shows for the first time that a strong instruction-tuned code LLM can result from self-alignment rather than distillation.more » « less
