Charvi Rastogi
I am a Ph.D. student in the Machine Learning Department at Carnegie Mellon University, where I am co-advised by Nihar Shah and Ken Holstein. I have been lucky to collaborate with Sivaraman Balakrishnan. I am interested in using tools in statistics, machine learning, and HCI towards effective human-AI collaboration for a variety of tasks, such as decision-making, auditing, crowdsourcing. I am deeply passionate about using my skills to address gaps in socio-technical systems to help make them useful in practice, when possible.
My research is generously supported by a J.P. Morgan AI Research Fellowship and a IBM PhD Fellowship.
I have spent some fun summers working at Microsoft Research Redmond, IBM TJ Watson Research Center and Syracuse University, NY. In a past life, I was a wide-eyed undergrad at Indian Institute of Technology Bombay.
CV. Google Scholar.
Preprints
Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models
Charvi Rastogi∗, Alicia Parrish∗, Hannah Kirk∗, Jessica Quaye∗, Oana Inel∗, Max Bartolo∗, Juan Ciro, Rafael Mosquera, Addison Howard, Will Cukierski, D. Sculley, Vijay Janapa Reddi, and Lora Aroyo.
arXiv preprint 2023; featured on the Google Research blog.How do Authors' Perceptions of their Papers Compare with Co-authors' Perceptions and Peer-review Decisions?
Charvi Rastogi, Ivan Stelmakh, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, Zhenyu Xue, Hal Daumé III, Emma Pierson, and Nihar B. Shah
arXiv preprint 2023; featured on Communications of ACM blog and NeurIPS blog.
Publications, Presentations, and Posters
A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementarity
Charvi Rastogi*, Leqi Liu*, Ken Holstein, Hoda Heidari,
Poster presented at HMCAT Workshop (ICML 2022); EAAMO 2022; AAAI Proceedings of HCOMP 2023; featured on the CASMI blogSupporting Human-AI Collaboration in Auditing LLMs with LLMs
Charvi Rastogi, Marco Tulio Ribeiro, Nicholas King, Harsha Nori, Saleema Amershi
ACM Proceedings of AIES 202; featured on the Montreal AI Ethics Institute blog.DataPerf: Benchmarks for data-centric AI development.
Mark Mazumder, [+43 authors].
Proceedings of the NeurIPS 2023 Datasets and Benchmarks Track; arXivTo ArXiv or not to ArXiv: A Study Quantifying Pros and Cons of Posting Preprints Online
Charvi Rastogi*, Ivan Stelmakh*, Xinwei Shen, Marina Meila, Federico Echenique, Shuchi Chawla, Nihar B. Shah
Peer Review Congress (Abstract) 2022; arXiv.Cite-seeing and Reviewing: A Study on Citation Bias in Peer Review
Charvi Rastogi*, Ivan Stelmakh*, Ryan Liu, Shuchi Chawla, Federico Echenique, Nihar B. Shah
Peer Review Congress (Abstract) 2022; Full version in PLOS ONE; arXivNo Rose for MLE: Inadmissibility of MLE for Evaluation Aggregation Under Levels of Expertise
Charvi Rastogi, Ivan Stelmakh, Nihar B. Shah, Sivaraman Balakrishnan
IEEE ISIT 2022. Link to the full version.Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making.
Charvi Rastogi, Yunfeng Zhang, Dennis Wei, Kush R. Varshney, Amit Dhurandhar, Richard Tomsett
Proceedings of CSCW 2022. ACM. Video Presentation.A Large Scale Randomized Controlled Trial on Herding in Peer-Review Discussions
Ivan Stelmakh, Charvi Rastogi, Nihar B. Shah, Aarti Singh, Hal Daumé III
Peer Review Congress (Abstract) 2022; Full version in PLOS ONE; arXivTwo-Sample Testing on Ranked Preference Data and the Role of Modeling Assumptions.
Charvi Rastogi, Sivaraman Balakrishnan, Nihar B. Shah, Aarti Singh
Shorter version presented at IEEE ISIT 2020 - Slides, Video Presentation; Longer version published in JMLR 2022; arXiv
A spectral approach for the design of experiments: Design, analysis and algorithms
Bhavya Kailkhura, Jayaraman J. Thiagarajan, Charvi Rastogi, Pramod K. Varshney, Peer-Timo Bremer
The Journal of Machine Learning Research, 2019; arXiv
Winner of 2019 S&T Excellence in Publication awardMobile Sensing of Two-Dimensional Bandlimited Fields on Random Paths
Charvi Rastogi, Animesh Kumar
arXivNon-bandlimited Field Estimation with Location Unaware Mobile Sensors
Charvi Rastogi, Animesh Kumar
Poster presented at CSCIT'17
Collected Resources for Grad Students
Here is a form designed to help facilitate students checking in with their advisors (it has been used by SCS PhD students and received positive reviews!)
Here is a blog post to help new (and old) grad students through the immensely difficult task of (re) choosing their advisor
Here is a piece of research with helpful guidelines (contextualized with grad students' lived experiences) to empower students in focusing on community and mental health