Human-AI Collaboration in a Student Discussion Forum

被引:0
|
作者
Laney, Mason [1 ]
Dewan, Prasun [1 ]
机构
[1] Univ North Carolina Chapel Hill, Chapel Hill, NC 27599 USA
关键词
D O I
10.1145/3640544.3645215
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The recent public releases of AI tools such as ChatGPT have forced computer science educators to reconsider how they teach. These tools have demonstrated considerable ability to generate code and answer conceptual questions, rendering them incredibly useful for completing CS coursework. While overreliance on AI tools could hinder students' learning, we believe they have the potential to be a helpful resource for both students and instructors alike. We propose a novel system for instructor-mediated GPT interaction in a class discussion board. By automatically generating draft responses to student forum posts, GPT can help Teaching Assistants (TAs) respond to student questions in a more timely manner, giving students an avenue to receive fast, quality feedback on their solutions without turning to ChatGPT directly. Additionally, since they are involved in the process, instructors can ensure that the information students receive is accurate, and can provide students with incremental hints that encourage them to engage critically with the material, rather than just copying an AI-generated snippet of code. We utilize Piazza-a popular educational forum where TAs help students via text exchanges-as a venue for GPT-assisted TA responses to student questions. These student questions are sent to GPT-4 alongside assignment instructions and a customizable prompt, both of which are stored in editable instructor-only Piazza posts. We demonstrate an initial implementation of this system, and provide examples of student questions that highlight its benefits.
引用
收藏
页码:74 / 77
页数:4
相关论文
共 50 条
  • [1] Emotions in Human-AI Collaboration
    Ferrada, Filipa
    Camarinha-Matos, Luis M.
    NAVIGATING UNPREDICTABILITY: COLLABORATIVE NETWORKS IN NON-LINEAR WORLDS, PRO-VE 2024, PT I, 2024, 726 : 101 - 117
  • [2] Human-AI Collaboration with Bandit Feedback
    Gao, Ruijiang
    Saar-Tsechansky, Maytal
    De-Arteaga, Maria
    Han, Ligong
    Lee, Min Kyung
    Lease, Matthew
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 1722 - 1728
  • [3] Human-AI Collaboration in Recruitment and Selection
    Natarajan, Neil
    PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 7089 - 7090
  • [4] POSTER: A Teacher-Student with Human Feedback Model for Human-AI Collaboration in Cybersecurity
    Chowdhury, Abdullahi
    Ashenden, Debi
    Pogrebna, Ganna
    Nguyen, Hung
    PROCEEDINGS OF THE 2023 ACM ASIA CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, ASIA CCS 2023, 2023, : 1040 - 1042
  • [5] Rethinking Fairness for Human-AI Collaboration
    Ge, Haosen
    Bastani, Hamsa
    Bastani, Osbert
    15TH INNOVATIONS IN THEORETICAL COMPUTER SCIENCE CONFERENCE, ITCS 2024, 2024,
  • [6] Diverse Conventions for Human-AI Collaboration
    Sarkar, Bidipta
    Shih, Andy
    Sadigh, Dorsa
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [7] AI in Education, Learner Control, and Human-AI Collaboration
    Brusilovsky, Peter
    INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION, 2024, 34 (01) : 122 - 135
  • [8] Improving Human-AI Collaboration With Descriptions of AI Behavior
    Cabrera Á.A.
    Perer A.
    Hong J.I.
    Proc. ACM Hum. Comput. Interact., 2023, CSCW1
  • [9] AI in Education, Learner Control, and Human-AI Collaboration
    Peter Brusilovsky
    International Journal of Artificial Intelligence in Education, 2024, 34 : 122 - 135
  • [10] Specifying AI Objectives as a Human-AI Collaboration Problem
    Dragan, Anca
    AIES '19: PROCEEDINGS OF THE 2019 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, 2019, : 329 - 329