Monica Agrawal @ ICML

A person searching for risks of surgery. A traditional search engine would surface websites that would likely include both pros and cons of the surgery. However, RAG results only excerpt the cons.

Excited to be at #ICML2025 to present our paper on 'pragmatic misalignment' in (deployed!) RAG systems: narrowly "accurate" responses that can be profoundly misinterpreted by readers.

It's especially dangerous for consequential domains like medicine! arxiv.org/pdf/2502.14898

15.07.2025 17:15 — 👍 11    🔁 2    💬 0    📌 1

thanks, Maria!

02.07.2025 01:52 — 👍 2    🔁 0    💬 0    📌 0

Three step process in our paper. Step 1: Test Clinical Knowledge (Clinical Jargon Understanding and Unsupported Medical Claims) Step 2: Discover Correlation with Pretraining Data Step 3: Analyze Sources of Data

🩺 General LLMs perform well on clinical NLP tasks, even though they never see EHR data. How?

🚀 Our CHIL 2025 paper, led by my PhD student Furong Jia, probes the pre-training datasets behind popular LLMs to investigate how online medical sources drive performance.

📄 Paper: arxiv.org/abs/2505.15024

01.07.2025 17:08 — 👍 6    🔁 0    💬 0    📌 1

The AHLI CHIL Doctoral Symposium deadline is fast approaching!

🎓 Apply by March 15, 2025 at chil.ahli.cc/submit/docto...

#CHIL2025

05.03.2025 16:37 — 👍 3    🔁 3    💬 0    📌 0

Using Large Language Models to Promote Health Equity While the discussion about the effects of large language models (LLMs) on health equity has been largely cautionary, LLMs also present significant opportunities for improving health equity. We high...

Free access link: ai.nejm.org/stoken/defau...

This is joint work with @dmshanmugam.bsky.social , @rajmovva.bsky.social, Jon Kleinberg, @monicaagrawal.bsky.social, @mdredze.bsky.social, Kadija Ferryman, Judy Wawira Gichoya, @jurafsky.bsky.social, Pang Wei Koh, @karenlevy.bsky.social...

13.01.2025 17:51 — 👍 10    🔁 1    💬 1    📌 0

Our article on using LLMs to promote health equity is out in New England Journal of Medicine AI!

85% of equity-related LLM papers focus on *harms*.

But also vital are the equity-related *opportunities* LLMs create: detecting bias, extracting structured data, and improving access to health info.

13.01.2025 17:51 — 👍 25    🔁 7    💬 1    📌 0

We have a new review on generative AI in medicine, to appear in the Annual Review of Biomedical Data Science! We cover over 250 papers in the recent literature to provide an updated overview of use cases and challenges for generative AI in medicine.

18.12.2024 16:13 — 👍 23    🔁 8    💬 1    📌 2

I am recruiting PhD students at Duke!

Please apply to Duke CS or CBB if you are interested in developing new methods and paradigms for NLP/LLMs in healthcare.
For details, see here: monicaagrawal.com/home/researc....

18.11.2024 20:16 — 👍 13    🔁 6    💬 0    📌 0

I'd love to be added -- thanks!

13.11.2024 14:51 — 👍 3    🔁 0    💬 0    📌 0