Monica Munnangi

Monica Munnangi


🚀 On the Job Market: Research Scientist / ML Scientist Roles

I specialize in Natural Language Processing in knowledge intensive domains , building evaluation frameworks that ensure models are reliable in high-stakes settings.

  • Research: Knowledge Augmentation, RAG, Clinical NLP, Instruction Sensitivity, Fine-tuning LLMs
  • Experience: Internships at AI2 and Stanford Medicine (Shah Lab).

If there's a good fit, please contact me here.

I am a PhD candidate at Khoury College of Computer Science advised by Prof. Saiph Savage and a member of the Civic A.I. Lab. I interned at Stanford School of Medicine, Shah Lab advised by Jason Fries. I had a fun summer '23 interning at Allen Institute for AI advised by Aakanksha Naik.

My current research interests are generally around improving the performance of LLMs: how they use information, and how to evaluate their performance. I also work on the improving the safety, reliability, and real-world performance of large language models in high-stakes settings. I develop alignment methods through instruction tuning, domain-specific pretraining, supervised fine-tuning, and multi-turn evaluation. While much of my work is grounded in healthcare applications, the approaches I develop generalize to broader domains where trustworthy AI is essential.

Prior to PhD, I graduated from UMass Amherst, with a Masters in Computer Science. During this time, I interned at GE Healthcare as as Data Scientist where I worked on computer vision for medical imaging. I've done my undergrad at Vellore Institute of Technology, Chennai.

Email  /  CV  /  Google Scholar  /  Twitter  /  Medium

profile photo
Research Interests

Clinical Natural Language Processing, Retrieval for Large Language Models, Retrieval Augmented Generation and Robustness of LLMs

Updates
January 2026:I am a Teaching Assistant for Seminar in Human Computer Interaction 🤖: Globally Aware AI: Designing and Creating Intelligent Interfaces Across Cultures
July 2025:Our paper titled "FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs" to appear at MLHC 2025 ⚕️, Mayo Clinic, MN
August 2024: Interned at Shah lab, advised by Jason Fries, in sunny California ☀️
August 2024:Became a Ph.D. Candidate 🎉
June 2024:Our paper titled "Open (Clinical) LLMs are Sensitive to Instruction Phrasings" to appear at BioNLP at 🐘 ACL 2024 in Thailand
March 2024:Our paper titled "On-the-fly Definition Augmentation of LLMs for Biomedical NER" to appear at 🌄 NAACL 2024 in Mexico City
August 2023: Interned at Allen Institute for AI, fortunate to work with Aakanksha Naik , Sergey Feldman and Tom Hope, in beautiful Seattle 🏔
January 2023:I am a Teaching Assistant for Unsupervised Machine Learning and Data Mining in the Spring '23 semester
September 2022:I am a Teaching Assistant for 6220 Data Mining Techniques in the Fall '22 semester
September 2021: Started my PhD at Khoury College of Computer Science



Publications / Projects

FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs

Monica Munnangi*, Akshay Swaminathan*, Jason Alan Fries*, Jenelle Jindal, Sanjana Narayanan, Ivan Lopez, Lucia Tu, Philip Chung, Jesutofunmi A. Omiye, Mehr Kashyap, Nigam Shah

Accepted to MLHC 2025

PDF arXiv Code

Open (Clinical) LLMs are Sensitive to Instruction Phrasings

Alberto Mario Ceballos Arroyo*, Monica Munnangi*, Jiuding Sun, Karen Y.C. Zhang, Denis Jered McInerney, Byron C. Wallace, Silvio Amir

Accepted to BioNLP at ACL 2024

PDF arXiv Code

On-the-fly Definition Augmentation of LLMs for Biomedical NER

Monica Munnangi, Sergey Feldman, Byron C Wallace, Silvio Amir, Tom Hope, Aakanksha Naik

Accepted to NAACL 2024

PDF arXiv Code

Chest Tube Detection on Chest X-Ray Images Using Convolutional Deep Neural Networks

Khaled Younis, Yash Shah, Monica Munnangi, Katelyn Nye, Gireesha Rao, John M. Sabol

Accepted to European Society of Radiology (ECR) 2020, EPOS Scientific Poster.

PDF arXiv

A Brief History of Named Entity Recognition

Monica Munnangi


PDF arXiv

Auto generation of Image Captions for Medical Images

Monica Munnangi, Anubha Thandley



PDF arXiv


Teaching and Mentoring
  • Teaching Assistant for Unsupervised Machine Learning and Data Mining assisted Prof. Pavlu Virgil at Northeastern University in Spring 2023 semester
  • Teaching Assistant for Unsupervised Data Mining and assisted Prof. Pavlu Virgil at Northeastern University in Fall 2022 semester.
  • Co-advised a cohort of graduate students for a project titled Leveraging knowledge distillation for efficient on-device deployment of deep learning models in medical imaging [Naik, A. et al.] published in Society for Imaging Informatics in MCMI in Medical Imaging, Nov 2020.
  • Teaching Assistant for the course Database Management Systems and assisted Prof. Muralidhar A. at Vellore Institute of Technology in the Fall 2017 semester.
Academic Service
  • Communications chair (Organizing Committee) Conference on Health, Inference and Learning (CHIL), 2024
  • Program Committee at Human-centered LLMs workshop, ACL 2024
  • Logistics co-chair (Organizing Committee) for CHIL, 2023
  • Reviewer: ML4H 2020, 2021, 2022, 2023, 2024, COLING 2025
  • Program Committee at User-centered Natural Language Processing Workshop, WWW 2022
  • Student reviewer at Northeastern University’s CS PhD Admissions Committee 2022
Awards and Grants
  • Student Grant for NeurIPS 2020
  • Student Grant for EMNLP 2020
  • Central Board of Secondary Education Excellence award for outstanding performance in AISSE 2014
  • City topper, Science Olympiad Foundation - National Science Olympiad 2012
Selected Reading
Extra-Curriculars and Voluntary Work
National Science Olympiad

SOF is an Educational Organization popularizing academic competition and assisting development of competitive spirit among school children. I was awarded the School Topper in Grade 10.

Technocrats

Software Developer - 2016 to 2017 ; Team Technocrats is VIT Chennai’s official robotics team. Technocrats incorporates students from different branches who share a common passion for robotics and each one showcases their talent and skill in their particular field.

Hackathons

Participated in the MIT Hacking Medicine - May 2019 and co-developed OraNet which is a mobile application which would assist a clinician to screen patients for oral cancer in a quick and cost effective way.Participated in the HackHer413 and co-developed an algorithm to detect Wild animals in the images and gives information about the animals.

Model United Nations

Represented Spain in the United Nations Development Program and was an honorable mention in a 4 day Model United Nations in Hyderabad in August 2013.

Represented Spain in the United Nations Environmental Program and was an honorable mention in a 3 day Model United Nations in BITS Goa in February 2015.

The Orange Leaf, Hyderabad

Part of an event at DESIRE Society, Hyderabad - Serving children affected with HIV/AIDS.
Volunteer of an event at Sivananda Rehabilation Home, Hyderabad - To serve the needs of people affected by leprosy.
Volunteered a fund raising event, organized a 5K run in Hyderabad.


Credits : Jon Barron for the template.