Publications
Leveraging Past Assignments to Determine If Students Are Using ChatGPT for Their Essays
Yuhui Zhao, Chunhao Zao, Rohit Sridhar, Christopher Cui, Thad Starner
TLDR: Traditional ML methods can differientiate between human and LLM generated answers for specific questions given a ground-truth corpus of both human-written and LLM-written answers.
Published in: Proceedings of the Tenth ACM Conference on Learning@ Scale 2024
Examinator v4.0: Cheating Detection in Online Take-Home Exams
Christopher Cui, Jui-Tse Hung, Vaibhav Malhotra, Hardik Goel, Raghav Apoorv, Thad Starner
equal contribution
TLDR: Using answer timestamps and decision trees to catch cheaters. Extension of Examintor v3
Published in: Proceedings of the Tenth ACM Conference on Learning@ Scale 2024
Socratic Mind: Scalable Oral Assessment Powered By AI
Jui-Tse Hung, Christopher Cui, Diana M. Popescu, Saurabh Chatterjee, Thad Starner
TLDR: Building an AI to evaluate student understanding of concepts through interviews. Try a demo at socraticmind.com.
Published in: Proceedings of the Tenth ACM Conference on Learning@ Scale 2024
Answer Watermarking: Using Answer Generation Assistance Tools to Find Evidence of Cheating
Christopher Cui, Jui-Tse Hung, Pranav Sharma, Saurabh Chatterjee, Thad Starner
shared first author
TLDR: Catching copy-pasting cheaters with invisible byte-characters
Published in: Proceedings of the Tenth ACM Conference on Learning@ Scale 2024
A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds
Christopher Cui, Xiangyu Peng, Mark Riedl
TLDR: Quickly training roleplaying RL agents using RL agents pre-trained to play other roles in a open-world text game.
Pre-print
Thespian: Multi-Character Text Role-Playing Game Agents
Christopher Cui, Xiangyu Peng, Mark O. Riedl
TLDR: RL agents that can roleplay different characters in a open-world text game.
Published in: Proceedings of the AIIDE Workshop on Experimental AI in Games (EXAG) 2023
Story Shaping: Teaching Agents Human-like Behavior with Stories
Xiangyu Peng, Christopher Cui, Wei Zhou, Renee Jia, Mark O. Riedl
equal contribution
TLDR: Using stories to train RL agents
Published in: Proceedings of the 19th AAAI Conference on Artificial Intelligence in Interactive and Digital Entertainment (AIIDE) 2023
Examinator v3.0: Cheating Detection in Online Take-Home Exams
Jui-Tse Hung, Christopher Cui, Varun Agarwal, Saurabh Chatterjee, Raghav Apoorv, Rocko Graziano, Thad Starner
TLDR: Statistical analysis on student responses to catch cheaters
Published in: Proceedings of the Tenth ACM Conference on Learning@ Scale 2023
Neural Story Planning
Anbang Ye, Christopher Cui, Taiwei Shi, Mark O. Riedl
TLDR: Using LLMs (before they were large) to generate stories by backwards chaining preconditions and effects
Published in: Proceedings of the AAAI Workshop on Creative AI Across Modalities 2023