Back to all keywords
Generative AI
9 items tagged with “Generative AI”
Publications
Essays
- CHI 2026 | Everyone Has an LLM — Why Do Technical People Still Win?Even with the same LLM, technical experience still strongly predicts performance. What really widens the gap is planning, expression, understanding, and verification.
- CHI 2026 | An AI Persona Is Not Behavior Control — Bias Still Needs CalibrationCoBRA turns classic social experiments into a behavioral ruler for agents, making cognitive bias a measurable, tunable, reproducible control variable instead of a prompt wish.
- CHI 2026 | AI Design Tools Should Leave a Trail of Team Thinking, Not Only ResultsCoNode organizes AI generation into trackable, reusable, recombinable team knowledge, and validates its value with two rounds of user research.
- DIS 2026 | AI Science Editing Should Show Tradeoffs, Not Only VersionsSpatial Balancing maps scientific rigor and narrative appeal onto a spatial canvas, helping authors keep their bearings across rounds of AI revision.
- AI Trust Research | Explaining Reasoning Does Not Equal Being TrustworthyThis arXiv study finds that LLM reasoning text changes trust and how people inspect evidence, but does not automatically improve decision accuracy.
- IEEE TSE 2026 | Copilot Helps Students Get More Answers Right — and Pulls More Attention into DebuggingAn eye-tracking study with 50 students shows that Copilot raised task accuracy while also increasing completion time and visual cognitive effort.
- CHI 2026 | AI Can Save Teachers Time — But Not Classroom JudgmentInterviews with 22 teachers show that generative AI can ease repetitive planning work, yet what teachers guard most carefully is professional judgment, relationships, and responsibility.
- CHI 2026 | AI Sparked More Ideas — Why Did 18 of 30 Students Converge on Similar Designs?The AI group left 291 ideas versus 89 for sketching, yet image concepts still converged. This classroom study of 61 design students separates idea count, design intent, and creativity ratings.