Hi, I am a Ph.D. student at Harvard-MGB AIM, jointly with Maastricht University, under the guidance of Hugo Aerts, Ph.D. and Danielle S. Bitterman, M.D. I am the recipient of the 2024 Google PhD Fellowship in Natural Language Processing, mentored by Asma Ghandeharioun, Ph.D. I am also affiliated with the Boston Children's Hospital Computational Health Informatics Program (CHIP), where we have the privilege of collaborating closely with Guergana Savova, Ph.D. and Tim Miller, Ph.D.
On one hand, I am deeply interested in the knowledge and features representation of large language models, aiming to develop more interpretable AI systems for critical domains such as healthcare. On the other hand, I am passionate about enhancing patient communication and establishing robust safety evaluation methods for high-stakes tasks. It is crucial to assess the impact of AI on all healthcare stakeholders—including patients, providers, and others.
My research has been featured in major media outlets such as Bloomberg, The New York Times, NBC, and New Scientist, among others. It has also been highlighted by government agencies including the FDA, NCI, and NIH, and has been cited in U.S. congressional hearings.
During COVID-19, I completed with M.S. in Computational Linguistics from Brandeis University, where I was fortunate to be advised by Professor Nianwen Xue Ph.D. where I fully explored my interests and met many wonderful people and friends. Before Brandeis, I spent 4 years as an undergraduate in Math, Japanese and Linguistics at St. Olaf College, really enjoyed my liberal arts education, click here if you want to learn more about my undergrad I'm a button.
During my free time, I enjoy basketball, dragonboat and kyudo 🏹.
If you want to work with me or my group, please email bittermanlab@gmail.com instead!
News
- [01/04/2025] Our paper on using LLMs to identify social determinants of health in electronic health records was the most cited journal-wide (Nature/NPJ Digital Medicine) in 2024! This paper was also selected for the AI and Data Science Year in Review 2024 at AMIA!
- [11/11/2024] Heading to EMNLP and wrote a blog post on what we learnt this year on various things in AI4healthcare.
- [10/10/2024] Our paper "WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation" is now available on arXiv.
- [09/15/2024] Honored to receive the 2024 Google PhD Fellowship in Natural Language Processing!
- [06/19/2024] RABBITS is out! We examined current biomedical benchmarks and found the language models are more familar with generic terms!
- [05/09/2024] Cross-Care is out! The first grounded bias benchmark that analyzes how pre-training data impacts model misalignment with real-world medical concepts.
- [04/02/2024] LCD Benchmark is out! Try this long clinical documents benchmark that LLMs are bad at!
- [11/07/2023] Our SDoH paper got accepted at Nature Digital Medicine, front page featured article from Jan-May 2024. Highlight research at NCI!
- [08/24/2023] Check out our work and editorial highlights @ JAMA Onc. Also used during US congress hearing!
Selected Publications
(* indicates equal contribution)
Mentoring
Students and projects
- SYNPO: Synthetic Data Augmentation Through Iterative Preference Optimization on LLMs for Clinical Problem Summarization, Shayan Chowdhury | 2024 Summer
- Mapping Bias in MLLMs: Signposts, Pitfalls, and the Road Ahead, Kuleen Sasse and Jackson Pond | 2024 Summer
- Yanan (Lance) Lu (Harvard DBMI, 2022-2023) - Now MLE at TikTok
- Vikram Goddla (High School, 2022-2023) - Now at Harvard College
Honors and Service
Honors
- Google PhD Fellowship in Natural Language Processing, 2024
- CHIL Doctoral Consortium, 2024
- Brandeis Merit Scholarship, 2020
- JASSO Scholarship, 日本文部科学省, 2019
- National Japanese Exam Silver Prize, AATJ 全米日本語教育学会, 2019
- Henry Luce Research Grant, Henry Luce Foundation, 2018
- Pi Mu Epsilon Society, National Math honor society, 2018
Service
- Peer Reviewer: ACL, EMNLP, NAACL, EACL, ICLR
- Program Committee: Clinical NLP Workshop 2023, 24
- Journal Reviewer: JAMIA, JBI, JMIR, JNCI, Nature communication, npj Digital Medicine, Nature Medicine
Invited Talks
- Shan Chen; UAB Annual Methods Symposium - Tutorial on how much bias is in LLMs in clinical settings; 2025
- Shan Chen; MIT HST 953 - Towards More Robust Large Language Models Applications in Clinical Settings; 2024
- Shan Chen; City of Hope - The Role and Risks of Large Language Models in Clinical Settings; 2024
- Shan Chen; Harvard - Beacon hill lecture seminars: current progress of AI4Healthcare; 2024