Michael Cooper
@coopermj.bsky.social
We red-teamed modern LLMs with practicing clinicians using real clinical scenarios.
The LLMs:
✅ Made up lab test scores
✅ Gave bad surgical advice
✅ Claimed two identical X-rays looked different
Here’s what this means for LLMs in healthcare.
📄 arxiv.org/abs/2505.00467
🧵 (1/)
The LLMs:
✅ Made up lab test scores
✅ Gave bad surgical advice
✅ Claimed two identical X-rays looked different
Here’s what this means for LLMs in healthcare.
📄 arxiv.org/abs/2505.00467
🧵 (1/)
Red Teaming Large Language Models for Healthcare
We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for Healthcare, which took...
arxiv.org
June 25, 2025 at 5:27 PM
We red-teamed modern LLMs with practicing clinicians using real clinical scenarios.
The LLMs:
✅ Made up lab test scores
✅ Gave bad surgical advice
✅ Claimed two identical X-rays looked different
Here’s what this means for LLMs in healthcare.
📄 arxiv.org/abs/2505.00467
🧵 (1/)
The LLMs:
✅ Made up lab test scores
✅ Gave bad surgical advice
✅ Claimed two identical X-rays looked different
Here’s what this means for LLMs in healthcare.
📄 arxiv.org/abs/2505.00467
🧵 (1/)
🚨 This is the future of causal inference. 🚨👇
CausalPFN is a foundation model trained on simulated causal worlds—it estimates heterogeneous treatment effects in-context from observational data. No retraining. Just inference.
Oh, and it's SOTA. 🔥
A 𝘮𝘢𝘴𝘴𝘪𝘷𝘦 leap forward for the field. 🚀
CausalPFN is a foundation model trained on simulated causal worlds—it estimates heterogeneous treatment effects in-context from observational data. No retraining. Just inference.
Oh, and it's SOTA. 🔥
A 𝘮𝘢𝘴𝘴𝘪𝘷𝘦 leap forward for the field. 🚀
🚨 Introducing CausalPFN, a foundation model trained on simulated data for in-context causal effect estimation, based on prior-fitted networks (PFNs). Joint work with Hamid Kamkari, Layer6AI & @rahulgk.bsky.social 🧵[1/7]
📝 arxiv.org/abs/2506.07918
🔗 github.com/vdblm/Causal...
🗣️Oral@ICML SIM workshop
📝 arxiv.org/abs/2506.07918
🔗 github.com/vdblm/Causal...
🗣️Oral@ICML SIM workshop
June 11, 2025 at 2:53 PM
🚨 This is the future of causal inference. 🚨👇
CausalPFN is a foundation model trained on simulated causal worlds—it estimates heterogeneous treatment effects in-context from observational data. No retraining. Just inference.
Oh, and it's SOTA. 🔥
A 𝘮𝘢𝘴𝘴𝘪𝘷𝘦 leap forward for the field. 🚀
CausalPFN is a foundation model trained on simulated causal worlds—it estimates heterogeneous treatment effects in-context from observational data. No retraining. Just inference.
Oh, and it's SOTA. 🔥
A 𝘮𝘢𝘴𝘴𝘪𝘷𝘦 leap forward for the field. 🚀
Very grateful for the support from @torontosri.bsky.social—these resources stand to significantly advance my work applying modern machine learning to make liver transplant prioritization more equitable and efficient. 🚀
We're thrilled to announce the 2025–26 Schwartz Reisman Institute Graduate Fellows! 🎉
15 outstanding PhD students from @uoft.bsky.social will join our interdisciplinary community exploring how advanced technologies can better serve society.
Meet them 👉 srinstitute.utoronto.ca/news/schswar...
15 outstanding PhD students from @uoft.bsky.social will join our interdisciplinary community exploring how advanced technologies can better serve society.
Meet them 👉 srinstitute.utoronto.ca/news/schswar...
Schwartz Reisman Institute announces 2025–26 graduate fellows — Schwartz Reisman Institute
The Schwartz Reisman Institute for Technology and Society is proud to announce the appointment of fifteen new graduate fellows from across the University of Toronto.
srinstitute.utoronto.ca
June 11, 2025 at 2:51 AM
Very grateful for the support from @torontosri.bsky.social—these resources stand to significantly advance my work applying modern machine learning to make liver transplant prioritization more equitable and efficient. 🚀