Variation Lab Human-Computer Interaction @SEAS

We are the Variation Lab from Harvard SEAS. We build AI-resilient interfaces that help people notice, evaluate, and recover from AI choices during open-ended work like reading, writing, ideating, and sensemaking.

AI is powerful, but it can be wrong, contextually inappropriate, or subjectively bad—and suppress the user’s critical engagement and learning at the same time. The Variation Lab’s research is defining and refining our understanding of AI-resilient interfaces that help people use AI while (a) maintaining their ability to notice AI choices, e.g., by spurring curiosity and cognitive engagement through surfacing variation in the data and/or the AI’s outputs and (b) giving them the context necessary to evaluate whether those choices are wrong, or at least not right for them. This is critical during context- and preference-dominated open-ended tasks, like ideating, searching, sensemaking, and reading or writing text and code at scale.

AI-resilient interfaces improve AI safety, usability, and utility by working with, not against, human perception, attention, and cognition. To achieve this, we derive and disseminate design implications from cognitive science and empirical studies of novel system prototypes, even and especially when these implications fly in the face of common usability guidelines.

View Publications Meet People

Research Themes

Designing for hard-to-measure value

Recognizing activities whose value lies in the effort and experience itself, so AI assistance does not shortcut the meaning people would otherwise find.

AI-resilient interface design

Helping people notice AI choices and giving them the context to judge whether those choices are wrong, or simply not right for them.

Theory-connected systems

Building interfaces on theories of learning, attention, and emotion regulation, even when they defy common usability guidelines, and the infrastructure to do this across HCI.

Selected Publications

View all papers

AbstractExplorer: Leveraging Structure-Mapping Theory to Enhance Comparative Close Reading at Scale

Ziwei Gu, Joyce Zhou, Nina Lei, Jonathan K. Kummerfeld, Mahmood Jasim, Narges Mahyar, Elena L. Glassman

ACM Symposium on User Interface Software and Technology (Proc. UIST 2025)

DOI Paper

Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale

Priyan Vaithilingam, Munyeong Kim, Frida-Cecilia Acosta-Parenteau, Daniel Lee, Amine Mhedhbi, Elena L. Glassman, Ian Arawjo

ACM Symposium on User Interface Software and Technology (Proc. UIST 2025)

DOI Paper

Law is vulnerable to AI influence; interface design can help

Aileen Nielsen, Chelse Swoopes, Elena L. Glassman

SSRN 2025

Paper

Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories

Simret Araya Gebreegziabher, Yukun Yang, Elena L. Glassman(Co-last corresponding author), Toby Jia-Jun Li(Co-last corresponding author)

ACM CHI Conference on Human Factors in Computing Systems (Proc. CHI 2025)

Best Paper Award

DOI Paper

Supporting Sensemaking of Large Language Model Outputs at Scale

Katy Ilonka Gero, Chelse Swoopes, Ziwei Gu, Jonathan K. Kummerfeld, Elena L. Glassman

ACM CHI Conference on Human Factors in Computing Systems (Proc. CHI 2024)

Honorable Mention Award

DOI Paper

Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems

Zana Buçinca, Phoebe Lin, Krzysztof Z. Gajos, Elena L. Glassman

ACM International Conference on Intelligent User Interfaces (Proc. IUI 2020)

Best Paper Award

DOI Paper