Harsh Kumar

2026

Diagnosing and Repairing Persona Collapse in LLM Advice
Harsh Kumar, Karina Vold, Louis Tay, Ashton Anderson
request for preprint, under review

A Taxonomy of Value Alignment Problems: Subproblems and Solutions
Daniel R. Harris, Karina Vold, Harsh Kumar, Ashton Anderson
request for preprint, under review

Position: We Need Large Language Models Optimized For Our Well-Being
Ashton Anderson, Harsh Kumar, Louis Tay, Karina Vold
ICML 2026

When AI Gives Advice: Evaluating AI and Human Responses to Online Advice-Seeking for Well-Being
Harsh Kumar, Jasmine Chahal, Yuxuan Zhao, Zixuan Zhang, Anne Zhiyu Wei, Louis Tay, Ashton Anderson
CHI 2026

Investigating the Effects of LLM Use on Critical Thinking under Time Constraints: Access Timing and Time Availability
Jiayin Zhi, Harsh Kumar, Mina Lee
CHI 2026

Beyond the AI Tutor: Social Learning with LLM Agents
Harsh Kumar, Zimo Kang, Jonathan Vincentius, Ashton Anderson
preprint, under review

Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course
Ruiwei Xiao, Runlong Ye, Xinying Hou, Jionghao Wen, Harsh Kumar, Michael Liut, John Stamper
preprint, under review

Effects of an SMS Mental Health Intervention on Suicidal Ideation in Young Adults
J. Meyerhoff, E. Tack, S. Popowski, C. J. Krause, C. J. Karr, T. Nguyen, K. Rushton, E. Gray, M. J. Kwasny, M. Reddy, K. Lucas, I. Musabirov, H. Kumar, H. Song, T. Li, A. Bhattacharjee, J. J. Williams, R. Kornfield, D. C. Mohr
14th International Society for Research on Internet Interventions (ISRII) Scientific Meeting, Newcastle, Australia — Oct 2026 talk

2025

Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinking
Harsh Kumar, Jonathan Vincentius, Ewan Jordan, Ashton Anderson
CHI 2025 ● HONORABLE MENTION

Math Education with Large Language Models: Peril or Promise?
Harsh Kumar, David M. Rothschild, Daniel G. Goldstein, Jake M. Hofman
AIED 2025

Large Language Model Agents for Improving Engagement with Behavior Change Interventions: Application to Digital Mindfulness
Harsh Kumar, SuHyeon Yoo, Angela Zavaleta Bernuy, Jiakai Shi, Huayin Luo, Joseph Jay Williams, et al.
CSCW 2025 (PACM HCI)

Investigating the Role of Situational Disruptors in Engagement with Digital Mental Health Tools
Ananya Bhattacharjee, Joseph Jay Williams, Miranda Beltzer, Jonah Meyerhoff, Harsh Kumar, Haochen Song, et al.
CSCW 2025 (PACM HCI) ● HONORABLE MENTION

Platform-Based Adaptive Experimental Research in Education: Lessons Learned from the Digital Learning Challenge
Ilya Musabirov, Mohi Reza, Haochen Song, Steven Moore, Pan Chen, Harsh Kumar, Tong Li, John Stamper, et al.
LAK 2025

Understanding Help-Seeking Behavior of Students Using LLMs vs. Web Search for Writing SQL Queries
Harsh Kumar, Mohi Reza, Jeb Thomas-Mitchell, Ilya Musabirov, Lisa Zhang, Michael Liut
DataEd Workshop 2025 workshop

2024

Guiding Students in Using LLMs in Supported Learning Environments: Effects on Interaction Dynamics, Learner Performance, Confidence, and Trust
Harsh Kumar, Ilya Musabirov, Mohi Reza, Jiakai Shi, Xinyuan Wang, Joseph Jay Williams, Anastasia Kuzminykh, Michael Liut
CSCW 2024 (PACM HCI)

Supporting Self-Reflection at Scale with Large Language Models: Insights from Randomized Field Experiments in Classrooms
Harsh Kumar, Ruiwei Xiao, Benjamin Lawson, Ilya Musabirov, Jiakai Shi, Xinyuan Wang, Huayin Luo, Joseph Jay Williams, Anna Rafferty, John Stamper, Michael Liut
Learning@Scale 2024

Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health
Harsh Kumar, Tong Li, Jiakai Shi, Ilya Musabirov, Rachel Kornfield, Jonah Meyerhoff, et al.
AAAI 2024 (IAAI)

Disclosures & Disclaimers: Investigating the Impact of Transparency Disclosures and Reliability Disclaimers on Learner–LLM Interactions
Jessica Y. Bo*, Harsh Kumar*, Michael Liut, Ashton Anderson
HCOMP 2024

Small Steps over Time: A Longitudinal Usability Test of an Automated Interactive Text Messaging Intervention to Support Self-Management of Depression and Anxiety Symptoms
Jonah Meyerhoff, Miranda Beltzer, Sarah Popowski, Chris J. Karr, Theresa Nguyen, Joseph J. Williams, Charles J. Krause, Harsh Kumar, Ananya Bhattacharjee, David C. Mohr, Rachel Kornfield
Journal of Affective Disorders

A Preliminary Analysis of Students’ Help Requests with an LLM-Powered Chatbot when Completing CS1 Assignments
Ruiwei Xiao, Xinying Hou, Harsh Kumar, Steven Moore, John Stamper, Michael Liut
CSEDM Workshop @ EDM 2024 workshop

2023

Investigating the Role of Context in the Delivery of Text Messages for Supporting Psychological Wellbeing
Ananya Bhattacharjee, Joseph J. Williams, Jonah Meyerhoff, Harsh Kumar, Alex Mariakakis, Rachel Kornfield
CHI 2023 ● BEST PAPER AWARD

Exploring the Use of Large Language Models for Improving the Awareness of Mindfulness
Harsh Kumar, Yiyi Wang, Jiakai Shi, Ilya Musabirov, Norman A. S. Farb, Joseph J. Williams
CHI 2023 extended abstract

A Text Messaging Intervention to Support the Mental Health of Young Adults: User Engagement and Feedback from a Field Trial of an Intervention Prototype
Rachel Kornfield, Caitlin A. Stamatis, Ananya Bhattacharjee, Bei Pang, Theresa Nguyen, Joseph J. Williams, Harsh Kumar, et al.
Internet Interventions

Exploring the Potential of Chatbots to Provide Mental Well-Being Support for Computer Science Students
Harsh Kumar, Kunzhi Yu, Andrew Chung, Jiakai Shi, Joseph J. Williams
SIGCSE 2023 poster

QuickTA: Exploring the Design Space of Using Large Language Models to Provide Support to Students
Harsh Kumar, Ilya Musabirov, Joseph J. Williams, Michael Liut
LAK 2023 workshop

2022 and earlier

Exploring the Design of Prompts for Applying GPT-3 Based Chatbots: A Mental Wellbeing Case Study on Mechanical Turk
Harsh Kumar, Ilya Musabirov, Jiakai Shi, Adele Lauzon, Kwan Kiu Choy, Ofek Gross, Dana Kulzhabayeva, Joseph J. Williams
preprint (2022)

“Sounds like a Cheesy Radio Ad”: Using User Perspectives for Enhancing Digital COVID Vaccine Communication Strategies for Public Health Agencies
Harsh Kumar*, Taneea S. Agrawaal*, Kwan Kiu Choy, Jiakai Shi, Joseph J. Williams
CHI 2022 extended abstract

Safeguarding People against Social Media Frauds during the COVID-19 Oxygen Supply Crisis in India
Aayush Kapur, Himanshu Thakur, Harsh Kumar
ML4D Workshop @ NeurIPS 2021 workshop

Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization
Tong Li, Jacob Nogas, Haochen Song, Harsh Kumar, Audrey Durand, Anna Rafferty, Nina Deliu, Sofia S. Villar, Joseph J. Williams
preprint (2021)