Kundan Krishna, PhD Student
I am a PhD student at the Language Technologies Institute in the School of Computer Science at Carnegie Mellon University. I am fortunate to be co-advised by Prof Zachary Lipton and Prof Jeffrey Bigham. My current research interests lie in AI safety, pretraining, and summarization, with a special focus on applications in the medical domain. I graduated with a Bachelors degree in Computer Science from IIT Kanpur in 2016, and have also worked in the industry at Adobe, Amazon, Google and Abridge.
Research Interests: AI safety, NLP, Machine Learning for Healthcare
Publications
GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence
Kundan Krishna, Sanjana Ramprasad, Prakhar Gupta, Byron Wallace, Zachary Lipton, Jeffrey Bigham
arXiv (preprint), 2024USB: A Unified Summarization Benchmark Across Tasks and Domains
Kundan Krishna, Sanjana Ramprasad, Prakhar Gupta, Byron Wallace, Jeffrey Bigham, Zachary Lipton
EMNLP (Findings), 2023Downstream Datasets Make Surprisingly Good Pretraining Corpora
Kundan Krishna, Saurabh Garg, Jeffrey Bigham, Zachary Lipton
ACL 2023, 2023Improving the Robustness of Summarization Models by Detecting and Removing Input Noise
Kundan Krishna, Yao Zhao, Jie Ren, Balaji Lakshminarayanan, Jiaming Luo, Mohammad Saleh, Peter J. Liu
arXiv (preprint), 2022Does Pretraining for Summarization Require Knowledge Transfer?
Kundan Krishna, Jeffrey Bigham, Zachary Lipton
Findings of EMNLP, 2021Generating SOAP Notes from Doctor-Patient Conversations
Kundan Krishna, Sopan Khosla, Jeffrey Bigham, Jeffrey Bigham
Association for Computational Linguistics (ACL), 2021Extracting Structured Data from Doctor-Patient Conversations by Predicting Noteworthy Utterances
Kundan Krishna, Amy Pavel, Benjamin Schloss, Jeffrey Bigham, Zachary Lipton
AAAI Workshop Health Intelligence, 2020