6 papers
Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data
Simret Araya Gebreegziabher, Allison E Sproul, Yinuo Yang +3
Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implic…
Comparing Human Oversight Strategies for Computer-Use Agents
Chaoran Chen, Zhiping Zhang, Zeya Chen +9
LLM-powered computer-use agents (CUAs) are shifting users from direct manipulation to supervisory coordination. Existing oversight mechanisms, however, have largely been studied as…
Lessons from Real-World Deployment of a Cognition-Preserving Writing Tool: Students Actively Engage with Critical Thinking and Planning Affordances
Yinuo Yang, Zheng Zhang, Ningzhi Tang +5
AI-supported writing tools show strong potential for scaffolding students' learning of argumentative writing. Prior work has demonstrated the benefits of AI-supported cognitive sca…
SPARK: Real-Time Monitoring of Multi-Faceted Programming Exercises
Yinuo Yang, Ashley Ge Zhang, Steve Oney +1
Monitoring in-class programming exercises can help instructors identify struggling students and common challenges. However, understanding students' progress can be prohibitively di…
Editrail: Understanding AI Usage by Visualizing Student-AI Interaction in Code
Ashley Ge Zhang, Yan-Ru Jhou, Yinuo Yang +4
Programming instructors have diverse philosophies about integrating generative AI into their classes. Some encourage students to use AI, while others restrict or forbid it. Regardl…
GLITTER: An AI-assisted Platform for Material-Grounded Asynchronous Discussion in Flipped Learning
Weirui Peng, Yinuo Yang, Zheng Zhang +1
Flipped classrooms promote active learning by having students engage with materials independently before class, allowing in-class time for collaborative problem-solving. During thi…