Let's say you're trying to understand racial health disparities in the U.S. Does it matter which source of administrative race/ethnicity information you use? We analyzed a dataset of 5M+ patients with linked electronic health records and Census Bureau microdata to find out. 🧵👇
@sebkrier Appreciate the spotlight on our efforts to reduce regulatory bloat at RegLab (https://t.co/TwZMHFUQvM)! This is a great list, and we're working on projects across many of these domains.
10/ Check out the full paper, “Evaluating the impact of discordant and missing demographic information on population health assessments using linked electronic health records and Census Bureau microdata”, at https://t.co/SLJvnXtbVY, and our other work at https://t.co/J6aZffUUaN
Let's say you're trying to understand racial health disparities in the U.S. Does it matter which source of administrative race/ethnicity information you use? We analyzed a dataset of 5M+ patients with linked electronic health records and Census Bureau microdata to find out. 🧵👇
9/ It was also a personal honor to be able to do this work as a Census sworn researcher, and to work with awesome collaborators within a secure research environment at the U.S. Census Bureau. (This study survived DOGE and two government shutdowns! #iykyk)
At a time of increased focus on "government efficiency", this #EMNLP2025 accepted paper shows how LLMs can empower civil servants rather than replace them, keeping humans in the loop while reducing time spent on redundant and menial tasks. See more at https://t.co/J6aZffUUaN!
The EPA receives thousands of tips annually from the public about environmental violations. 80% of them shouldn’t even be going to the EPA, and the rest often get sent to the wrong division. We’ve built an LLM-based system to assist with tip routing. https://t.co/mCX8BowM9H
We developed a two-stage LLM pipeline by fine-tuning models on these tips. Stage 1 filters out tips that aren’t under the EPA’s jurisdiction, and Stage 2 routes remaining tips to the Civil or Criminal Division. We achieve 82.4% accuracy (compared to 31.8% in the current system).
✨ Very overdue update:
I'll be starting as an Assistant Professor in CS at University of Minnesota, Twin Cities, Fall 2026. I will be recruiting PhD students!!
Please help me spread the word! [Thread] 1/n
Thanks @KelseyTuoc for referencing our ADU study! Couldn't have said it better: "I don’t think we need better enforcement that would prevent this housing from getting built — we need fewer rules for people building much-needed housing!" RegLab is working on this with cities!
I wrote for the Argument today about all the ways our society is set up to reward cheating: strict rules, not really enforced, because we lack the will either to enforce them or to change them. https://t.co/XvrbGdP9Yc