近日，由广东智慧教育研究院与美国卡耐基梅隆大学、美国孟菲斯大学、美国密歇根大学、北京师范大学等团队共同举办的大模型赋能下一代内容生成和交互接口国际研讨会（International Workshop on Empowering Education with LLMs - the Next-Gen Interface and Content Generation）在东京圆满结束。
研讨会主页见：https://ai4ed.cc/workshops/aied2023
图1 研讨会特邀演讲嘉宾和主办单位
图2 研讨会主办地东京会议中心现场
本次讨论会的主题为大模型赋能下一代内容生成和交互接口，旨在汇集来自学术界和行业的研究人员和实践者，探索生成式人工智能在支持教与学方面的潜力，探讨在人机协作系统中使用大型语言模型（LLMs），讨论涉及学生、教师和其他人的不同人工智能伙伴关系如何有效地发挥作用，并进一步探讨与教育内容创作和评估相关的主题，LLMs的挑战和机遇，以及伦理考虑。
本次讨论会盛情邀请了国立台中教育大学校长郭伯臣、加利福尼亚大学伯克利分校（UC Berkely）教授Zachary Pardos和伍斯特理工学院（Worcester Polytechnic Institute）教授Neil Heffernan进行会议主旨演讲。
图3 国立台中教育大学校长郭伯臣进行主题报告
本次研讨会对来自全球各地的数十多篇投稿进行严格筛选，共有17篇论文被我们录取，其中有10篇论文进行了现场报告，另外7篇论文以视频录制的方式进行报告。
研讨会收录论文
1
Muntasir Hoq, Yang Shi, Juho Leinonen, Damilola Babalola, Collin Lynch and Bita Akram - Detecting ChatGPT-Generated Code in a CS1 Course。
2
Andrew Caines, Luca Benedetto, Shiva Taslimipoor, Christopher Davis, Yuan Gao, Øistein Andersen, Zheng Yuan, Mark Elliott, Russell Moore, Christopher Bryant, Marek Rei, Andrew Mullooly, Diane Nicholls and Paula Buttery - On the application of Large Language Models for language teaching and assessment technology.
3
Benjamin Nye, Dillon Mee and Mark G. Core - Generative Large Language Models for Dialog-Based Tutoring: An Early Consideration of Opportunities and Concerns.
4
Matyáš Boháček - The Unseen A+ Student: Evaluating the Performance and Detectability of Large Language Models in High School Assignments.
5
Bor-Chen Kuo, Frederic Chang and Zong-En Bai - Leveraging LLMs for Adaptive Testing and Learning in Taiwan Adaptive Learning Platform (TALP).
6
Andrew Oleny - Generating Multiple Choice Questions from A Textbook: LLMs Match Human Performance on Most Metrics.
7
Daniel Leiker, Sara Finnigan, Ashley Ricker Gyllen and Mutlu Cukurova - Prototyping the Use of Large Language Models (LLMs) for Adult Learning Content Creation at Scale.
8
Alex Goslen, Yeo Jin Kim, Jonathan Rowe and James Lester - Language Modeling for Plan Generation in Game-Base Learning Environments.
9
Kole Norberg, Husni Almoubayyed, Stephen Fancsali, Logan De Ley, Kyle Weldon, April Murphy and Steve Ritter - Rewriting Math Word Problems with Large Language Models.
10
Gautam Yadav, Ying-Jui Tseng and Xiaolin Ni - Contextualizing Problems to Student Interests at Scale in Intelligent Tutoring System Using Large Language Models.
11
Shashank Sonkar, Richard Baraniuk - DUPEd GPT: Can GPT do Knowledge Tracing?
12
Pragnya Sridhar, Aidan Doyle, Arav Agarwal, Christopher Bogart, Jaromir Savelka, Majd Sakr - Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives.
13
Md Rayhan Kabir, Fuhua (Oscar) Lin - An LLM-Powered Adaptive Practicing System.
14
Shouvik Ahmed Antu, Haiyan Cheng, Cindy K Roberts - Using LLM (Large Language Model) to Improve Efficiency for Literature Reviews in Undergraduate Research.
15
Katie Bainbridge, Candace Walkington, Armon Ibrahim, Iris Zhong, Debshila Basu Mallick, Julianna Washington, Richard Baraniuk - A Case Study using Large Language Models to Generate Metadata for Math Questions.
16
Sai Gattupalli, Will Lee, Danielle Allessio, Danielle Crabtree, Ivon Arroyo, Beverly Woolf - Exploring Pre-Service Teachers’ Perceptions of Large Language Models-Generated Hints in Online Mathematics Learning.
17
Qianou (Christina) Ma, Sherry (Tongshuang) Wu, Ken Koedinger - Is LLM the Better Programming Partner?
近年来，基于大模型的内容生成和交互接口已经成为当前人工智能教育的重要研究方向。大模型的应用能进一步促进人工智能教育的发展，为教育行业的智能化发展增添新动能。随着AI技术为教育行业赋能，学习者也能够体验到更加高效、便捷的学习体验，实现学习效率与学习结果的双重提升。广东智慧教育研究院将继续坚持源头创新、应用驱动和开放共享的原则，致力于在智慧教育领域开展体系化研究。我们将与国内外知名企业和机构合作，推动大语言模型的发展和应用，为推动智慧教育的进步和应用做出贡献。
