Significant Trends in CS Educational Material

Brusilovsky, Peter; Ericson, Barbara; Horstmann, Cay S.; Servin, Christian; Vahid, Frank; Zilles, Craig

doi:10.1145/3545947.3573353

Cited by 6 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One key finding was that students frequently copied the exercise questions as prompts and then used the AI-generated code without making any alterations to it. This reliance on the code generator is suggestive of the over-dependency problem [9][10][11]. To address this, CodeAid integrates guardrails to restrict the openended AI system from generating direct code solutions even if students ask for them.…”

Section: Writing and Debugging Codementioning

confidence: 99%

CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs

Kazemitabaar,

Ye,

Wang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

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.

show abstract

Section: Writing and Debugging Codementioning

confidence: 99%

CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs

Kazemitabaar,

Ye,

Wang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Instructors can utilize LLM-based code generation models to automate the generation of programming assignments, including sample answers with explanations and test cases. These models also facilitate code translation between programming languages [3], simplifying content creation. By leveraging these models, instructors can also generate novel exercise variations based on existing exercises [8].…”

Section: Teaching Practicesmentioning

confidence: 99%

“…[14] "GPT-3 can automatically create a checklist of common mistakes students might make regarding a given code snippet." [14] [ 13,17,3,1,20,14] Table 2: Learning practices using Code Generation Models independently while having access to an AI code generator powered by OpenAI Codex. To enable AI code generation, users input their desired code behavior in natural language using a textbox, and clicking the generate button inserts the code generated by OpenAI Codex.…”

Section: Educational Toolsmentioning

confidence: 99%

See 1 more Smart Citation

Use of AI-driven Code Generation Models in Teaching and Learning Programming: a Systematic Literature Review

Cambaz,

Zhang

2024

Proceedings of the 55th ACM Technical Symposium on Computer Science Education v. 1

View full text Add to dashboard Cite

The recent emergence of AI-driven code generation models can potentially transform programming education. To pinpoint the current state of research on using AI code generators to support learning and teaching programming, we conducted a systematic literature review with 21 papers published since 2018. The review presents the teaching and learning practices in programming education that utilize these models, the characteristics and performance indicators of the code generation models, and aspects to be considered when utilizing the models in programming education, including the risks and challenges of using code generation models for educational practices. AI code generators can be an assistive tool for both learners and instructors if the risks are mitigated.

show abstract

“…In the future, it may even be possible to generate a personalized Parsons problem, one that is based on a student's incorrect code solution using Large Language Models (LLMs), and then utilise LLMs to generate an explanation if the student successfully completes the coding task but does not understand their solution [15].…”

Section: Worked Examplesmentioning

confidence: 99%

Multi-Institutional Multi-National Studies of Parsons Problems

Ericson,

Pearce,

Rodger

et al. 2023

Proceedings of the 2023 Working Group Reports on Innovation and Technology in Computer Science Education

View full text Add to dashboard Cite

Significant Trends in CS Educational Material

Cited by 6 publications

References 0 publications

CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs

CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs

Use of AI-driven Code Generation Models in Teaching and Learning Programming: a Systematic Literature Review

Multi-Institutional Multi-National Studies of Parsons Problems

Contact Info

Product

Resources

About