icon

Deepak Varuvel Dennison

AboutPublicationsProjectsNotebook ↗CV ↗

Hello :)

I am Deepak, a PhD Student at Cornell University advised by Rene Kizilcec and Aditya Vashistha. I am interested in developing and evaluating culturally-aware AI technologies. My current research focuses on evaluating the cultural alignment of Large Language Models. More broadly, I am interested in Human-Computer Interaction, Human-AI Interaction, Responsible AI, and Learning Sciences.

Previously, I worked as a Research Assistant at Stanford with Dora Demszky and Victor Lee, researching the educational applications of emerging AI technologies.

Oh also, check out Tales For Tweens, an Inclusive and Progressive Storybook that I have created for Young Indians. Please consider sharing it with kids, parents, and educators! :)

Deepak Varuvel Dennison

Recent News

02/25Began as a volunteer for organizing the Thought Summit: LLMs And Society, hosted by the Global AI Initiative at Cornell University

01/25Stanford CESTA's Digital Publication Platform, which I helped build from the ground up, is now officially launched! 🎉

01/25Completed my field work in Karnataka for the user study of Shiksha Copilot in partnership with Microsoft Research India and Sikshana Foundation

09/24Second edition of Tales For Tweens, a book that I created for young Indians, is available in Amazon India

08/24Started my PhD at Cornell CIS in the Info Science program

03/24From Consumers to Critical Users: Prompty, an AI Literacy Tool for High School Students published in the Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-24). Link to the paper

Publications

From Consumers to Critical Users: Prompty, an AI Literacy Tool For High School Students

Deepak Varuvel Dennison,* Raycelle C. C. Garcia,* Parth Sarin, Jacob Wolf, Christine Bywater, Benjamin Xie and Victor R.Lee

AAAI-24: Proceedings of the AAAI Conference on Artificial Intelligence

Co-designing AI Education Curriculum with Cross-Disciplinary High School Teachers

Benjamin Xie, Parth Sarin,* Jacob Wolf,* Raycelle C. C. Garcia, Victoria Delaney, Isabel Sieh, Anika Fuloria, Deepak Varuvel Dennison, Christine Bywater, Victor R. Lee

AAAI-24: Proceedings of the AAAI Conference on Artificial Intelligence

Evaluating LLMs' Generation of Growth-Mindset Supportive Teacher Language

Margarett Clapper, Cameron Hecht, Michaela Jones, Nirel Jonesmitchell, Meghann Johnson, Deepak Dennison, Dorrotya Demszky and David Yeager

AIED2023 Workshop: Equity, Diversity, and Inclusion in Educational Technology Research and Development

Selected Projects

Shiksha CoPilot: An AI-powered Teacher Assistant for Learning Content generation

Microsoft Research India, Sikshana Foundation, Cornell University

I conduct a mixed-methods research study evaluating the usefulness of LLMs in supporting teachers for whom English is a second language in lesson planning and content generation. My research explores the challenges they face and how AI is transforming their workflows. I designed the study—including surveys, interviews, and log analysis—conducted fieldwork, and analyzed data to generate insights that inform the design of LLM-powered teacher assistants for low-resource schools in the developing world.... More

M-Powering Teacher: A Machine Learning Tool for Instructional Measurement and Feedback

Stanford University

I designed and developed data dashboards for a machine learning tool that analyzes diverse facets of a teacher's instruction and delivered a holistic report on classroom interaction. I worked closely with teachers and educational researchers to identify specific feedback needs aimed at improving classroom practices.... More

Code In Place: A free, human-centered, intro-to-coding course from Stanford University

Stanford University

I built the user interface for the automated AI-Feedback feature for Code In Place, a large-scale human-centered coding course offered by Stanford, to provide automated feedback to section leaders and students leading to improvement in learning outcomes. I worked closely with Professors Dora Demszky and Chris Piech to build the feature in accordance to the learning sciences literature and research specifications.... More

CRAFT: Empowering students with AI Literacy

Stanford University

I researched and developed a learning tool that could help students utilize Large Language Models in a critical way and effective way in their writing processes. The tool was designed under the guidance of Professor Victor Lee through a co-design process with students and teachers. While the co-design process offered insights into the unique needs of the students and teachers, the learning sciences literature helped in shaping the tool for pedagogical effectiveness.... More

Check out my public notebook for more :)

Email | LinkedIn| GitHub| Google Scholar

Thank you for dropping by! ❤️