Hello! I'm a second year PhD student in the Machine Learning Department at Carnegie Mellon University, advised by Fei Fang, and funded by an NSF Fellowship.
My research focuses on principled approaches to real-world decision-making, including topics such as resource allocation, explainability, and human-AI collaboration.
My work has been deployed to domains including food insecurity and behavioral health.
I previously obtained my MPhil in Advanced Computer Science on a Churchill Scholarship, where I worked with Mateja Jamnik to understand explainability through concept learning models.
I received my BS in Computer Science and Math from the University of Maryland, during which I worked with John Dickerson on fairness in rideshare, and with Jordan Boyd-Graber on entity linking algorithms.
If you want to chat about any of these topics, or just about research in general, feel free to reach out!
Most recent publications on Google Scholar.
‡ indicates equal contribution.
PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health Organizations
Gao Mo‡, Naveen Raman‡, Megan Chai, Cindy Peng, Shannon Pagdon, Nev Jones, Hong Shen, Peggy Swarbrick, and Fei Fang
Under Submission
Do Concept Bottleneck Models Obey Locality?
Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik
TMLR '25
Assortment Optimization for Matching Patients and Providers
Naveen Raman, Holly Wiberg
ML4H Findings '24
Global Rewards in Restless Multi-Armed Bandits
Naveen Raman, Ryan Shi, Fei Fang
NeurIPS '24
Understanding Inter-Concept Relationships in Concept-Based Models
Naveen Raman, Mateo Espinosa Zarlenga, Mateja Jamnik
ICML '24
PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health Organizations
Gao Mo‡, Naveen Raman‡, Megan Chai, Cindy Peng, Shannon Pagdon, Nev Jones, Hong Shen, Peggy Swarbrick, and Fei Fang
Under Submission
Do Concept Bottleneck Models Obey Locality?
Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo, Mateja Jamnik
TMLR '25
Large Language Models in Peer-Run Community Behavioral Health Services: Understanding Peer Specialists and Service Users’ Perspectives on Opportunities, Risks, and Mitigation Strategies
Megan Chai‡, Cindy Peng‡, Gao Mo, Naveen Raman, Shannon Pagdon, Fei Fang, Nev Jones, Peggy Swarbrick, Hong Shen
Under Submission
Contextual Budget Allocation for Food Rescue Volunteer Engagement
Ariana Tang, Naveen Raman, Fei Fang, Ryan Shi
Under Submission
Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
Santiago Cortes-Gomez, Naveen Raman, Aarti Singh, Bryan Wilder
ICML '25
Assortment Optimization for Matching Patients and Providers
Naveen Raman, Holly Wiberg
ML4H Findings '24
Global Rewards in Restless Multi-Armed Bandits
Naveen Raman, Ryan Shi, Fei Fang
NeurIPS '24
Understanding Inter-Concept Relationships in Concept-Based Models
Naveen Raman, Mateo Espinosa Zarlenga, Mateja Jamnik
ICML '24
Human Uncertainty in Concept-Based AI Systems
Katherine M. Collins, Matthew Barker, Mateo Espinosa Zarlenga, Naveen Raman, Umang Bhatt, Mateja Jamnik, Ilia Sucholutsky, Adrian Weller, Krishnamurthy Dvijotham
AIES '23
Improving Learning-to-Defer Algorithms Through Fine-Tuning
Naveen Raman, Michael Yee
NeurIPS '21 Human and Machine Decisions Workshop
Eliciting Bias in Question Answering Models through Ambiguity
Andrew Mao‡, Naveen Raman‡, Matthew Shu, Eric Li, Franklin Yang, Jordan Boyd-Graber
EMNLP '21 Machine Reading for Question Answering Workshop
Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling
Naveen Raman, Sanket Shah, John Dickerson
IJCAI '21
What more can Entity Linking do for Question Answering
Naveen Raman, Pedro Rodriguez, Jordan Boyd-Graber
NeurIPS '20: Human And Machine in-the-Loop Evaluation and Learning Strategies Workshop
Stress and Burnout in Open Source: Toward Finding, Understanding, and Mitigating Unhealthy Interactions.
Naveen Raman, Minxuan Cao, Yulia Tsvetkov, Christian Kaestner, Bogdan Vasilescu
ICSE '20 (NIER Track)