Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Breaking Barriers or Building Dependency? Exploring Team-LLM Collaboration in AI-infused Classroom Debate

Zihan Zhang, Black Sun, Pengcheng An

TL;DR

This study investigates how teams of design-history students collaborate with a large language model during in-class, high-velocity debates. Using three 1.5-hour debates over four weeks and ChatGPT-3.5, the authors document emergent team-LLM roles, questioning strategies, content filtering, and information-recording practices, revealing both benefits (reduced social anxiety, scaffolding for novices, rapid information access) and risks (information overload, cognitive dependency, low-quality outputs). They identify 10 themes and 29 sub-themes around interaction patterns and propose design implications for real-time, team-centered AI interfaces, including centralized memory, multimodal collaboration tools, and adaptive AI engagement to foster critical thinking. The findings emphasize that AI can enhance collaborative learning and discourse quality in fast-paced settings, while also highlighting challenges in autonomy and content reliability, informing future HCI research and educational practice in AI-enabled teamwork.

Abstract

Classroom debates are a unique form of collaborative learning characterized by fast-paced, high-intensity interactions that foster critical thinking and teamwork. Despite the recognized importance of debates, the role of AI tools, particularly LLM-based systems, in supporting this dynamic learning environment has been under-explored in HCI. This study addresses this opportunity by investigating the integration of LLM-based AI into real-time classroom debates. Over four weeks, 22 students in a Design History course participated in three rounds of debates with support from ChatGPT. The findings reveal how learners prompted the AI to offer insights, collaboratively processed its outputs, and divided labor in team-AI interactions. The study also surfaces key advantages of AI usage, reducing social anxiety, breaking communication barriers, and providing scaffolding for novices, alongside risks, such as information overload and cognitive dependency, which could limit learners' autonomy. We thereby discuss a set of nuanced implications for future HCI exploration.

Breaking Barriers or Building Dependency? Exploring Team-LLM Collaboration in AI-infused Classroom Debate

TL;DR

This study investigates how teams of design-history students collaborate with a large language model during in-class, high-velocity debates. Using three 1.5-hour debates over four weeks and ChatGPT-3.5, the authors document emergent team-LLM roles, questioning strategies, content filtering, and information-recording practices, revealing both benefits (reduced social anxiety, scaffolding for novices, rapid information access) and risks (information overload, cognitive dependency, low-quality outputs). They identify 10 themes and 29 sub-themes around interaction patterns and propose design implications for real-time, team-centered AI interfaces, including centralized memory, multimodal collaboration tools, and adaptive AI engagement to foster critical thinking. The findings emphasize that AI can enhance collaborative learning and discourse quality in fast-paced settings, while also highlighting challenges in autonomy and content reliability, informing future HCI research and educational practice in AI-enabled teamwork.

Abstract

Classroom debates are a unique form of collaborative learning characterized by fast-paced, high-intensity interactions that foster critical thinking and teamwork. Despite the recognized importance of debates, the role of AI tools, particularly LLM-based systems, in supporting this dynamic learning environment has been under-explored in HCI. This study addresses this opportunity by investigating the integration of LLM-based AI into real-time classroom debates. Over four weeks, 22 students in a Design History course participated in three rounds of debates with support from ChatGPT. The findings reveal how learners prompted the AI to offer insights, collaboratively processed its outputs, and divided labor in team-AI interactions. The study also surfaces key advantages of AI usage, reducing social anxiety, breaking communication barriers, and providing scaffolding for novices, alongside risks, such as information overload and cognitive dependency, which could limit learners' autonomy. We thereby discuss a set of nuanced implications for future HCI exploration.
Paper Structure (67 sections, 6 figures, 1 table)

This paper contains 67 sections, 6 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Human-AI Hybrid Collaborative and Multi-Technology Support in Education and Learning
  4. Traditional AI and Technology in Education
  5. LLMs in Education and Learning
  6. LLMs-infused Multi-learner Collaborative Learning
  7. Classroom Debate as Collaborative Learning
  8. METHODOLOGY
  9. Study Setup
  10. The Topics of Debates
  11. Debate 1: Is Ornament Crime?
  12. Debate 2: Is Public Taste or Professional Aesthetics Driving Contemporary Design Styles?
  13. Debate 3: Is Design the Icing on The Cake or a Timely Help in Adversity?
  14. Data Collection and Analysis
  15. FINDINGS 1: EMERGENT WAYS LEARNERS COLLABORATE WITH AI IN CLASSROOM DEBATES (RQ-1)
  16. ...and 52 more sections

Figures (6)

  • Figure 1: Information of Participants In the Classroom Debate
  • Figure 2: Overview of Human-AI Collaboration Learning Debate Scene and Process
  • Figure 3: Three Debate Processes and Debate Topics
  • Figure 4: Results for Question (1): "(Before the debate) How frequently do you use LLMs?"
  • Figure 5: Results for Question (2): "In which scenarios do you primarily use LLMs? (Multiple choice)"
  • ...and 1 more figures