mlsanityData to 13 Oct 2026

Learning from Teaching Assistants to Program with Subgoals: Exploring the Potential for AI Teaching Assistants

arXiv 2309.10419 ↗First posted 19 Sep 2023cs.HC cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

With recent advances in generative AI, conversational models like ChatGPT have become feasible candidates for TAs. We investigate the practicality of using generative AI as TAs in introductory programming education by examining novice learners' interaction with TAs in a subgoal learning environment. To compare the learners' interaction and perception of the AI and human TAs, we conducted a between-subject study with 20 novice programming learners. Learners solve programming tasks by producing subgoals and subsolutions with the guidance of a TA. Our study shows that learners can solve tasks faster with comparable scores with AI TAs. Learners' perception of the AI TA is on par with that of human TAs in terms of speed and comprehensiveness of the replies and helpfulness, difficulty, and satisfaction of the conversation. Finally, we suggest guidelines to better design and utilize generative AI as TAs in programming education from the result of our chat log analysis.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 16 of its 43 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

16 of 43 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,072
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,205
  4. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 743
  5. 2020Recipes for building an open-domain chatbotcited by 593
  6. 2022Few-shot training LLMs for project-specific code-summarizationcited by 129
  7. 2022Automatic Generation of Programming Exercises and Code Explanations using Large Language Modelscited by 125
  8. 2023Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPTcited by 125
  9. 2023Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programmingcited by 88
  10. 2022Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Bookcited by 84
  11. 2022The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialoguescited by 78
  12. 2022NatGen: Generative pre-training by "Naturalizing" source codecited by 54
4 more
  1. 2023Exploring the Responses of Large Language Models to Beginner Programmers' Help Requestscited by 46
  2. 2023Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Coursescited by 39
  3. 2023GPTutor: a ChatGPT-powered programming tool for code explanationcited by 23
  4. 2022Challenges Faced by Teaching Assistants in Computer Science Education Across Europecited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 3.

7 papers.

  1. 2024Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutorscited by 60
  2. 2023Can ChatGPT Play the Role of a Teaching Assistant in an Introductory Programming Course?cited by 6
  3. 2025"Would You Want an AI Tutor?" Understanding Stakeholder Perceptions of LLM-based Systems in the Classroomcited by 2
  4. 2024QACP: An Annotated Question Answering Dataset for Assisting Chinese Python Programming Learnerscited by 1
  5. 2025Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants' Question-Answering in Asynchronous Learning Environmentscited by 1
  6. 2023ChEDDAR: Student-ChatGPT Dialogue in EFL Writing Educationcited by 0
  7. 2025Small Language Models for Curriculum-based Guidancecited by 0