thanks for these comments, Ira :) :)

Wonderful to work with co-first author @sidhikabalachandar.bsky.social along with Alex Chouldechova, James Diao, Kadija Ferryman, Arjun Manrari, @stephenpfohl.bsky.social, Neil Powe, @rajiinio.bsky.social, and @emmapierson.bsky.social on this piece.

You can read it here! rdcu.be/e9uZa

The goal is not just to remove race from models. It's to build systems where race no longer adds predictive power — because the factors it proxies for have been directly measured and the inequities it captures have been addressed.

Computational approaches to removing race are often insufficient. Why? Race often correlates with (1) unmeasured but relevant factors, like genetic traits (which should be measured directly) and (2) systemic disparities, like racism (which should be addressed, not adjusted for).

We lay out principles for these evaluations: measure not just model fit but downstream effects on treatment/resource allocation; report results by racial subgroup; and pair simulated analyses with post-deployment studies tracking real-world consequences. Lots of room here for more work!

Before changing the inputs to a clinical algorithm, it is critical to evaluate the consequences. Past work in nephrology and pulmonology has shown that removing race can have unpredictable effects, and can both improve and worsen disparities, making it essential to conduct rigorous evaluations.

New in Nature Health: how might we move towards a world in which race is not used in clinical algorithms? We need (1) careful comparison of race-aware and race-neutral algorithms and (2) systemic efforts to address underlying disparities.

New paper! The Linear Representation Hypothesis is a powerful intuition for how language models work, but lacks formalization. We give a mathematical framework in which we can ask and answer a basic question: how many features can be stored under the hypothesis? 🧵 arxiv.org/abs/2602.11246

We found, for example, racial disparities in upward mobility —that is, the rate at which people move to higher-income areas varies according to the racial composition of their current area of residence, even after controlling for income levels. 6/9

Our paper “Inferring fine-grained migration patterns across the United States” is now out in @natcomms.nature.com! We released a new, highly granular migration dataset. 1/9

CS ArXiv recently banned “review and position” papers, but what are those? Do they include more generated content? Who is most affected by this change? @yanai.bsky.social and I dug into the data to find out!

Nearly 50% of Computers & Society papers might be censored, vs 3% of Computer Vision ‼️

Fairness in PCA-Based Recommenders

🎙️ I had a great time joining the Data Skeptic podcast to talk about my work on recommender systems

If you're interested in embeddings, aligning group preferences, or music recommendations, check out the episode below 👇

open.spotify.com/episode/6IsP...

I’m excited to share our new paper A Bayesian Model for Multi-stage Censoring, which I will present at #ML4H2025 in San Diego! 🧵 below:

🧠⚙️ Interested in decision theory+cogsci meets AI? Want to create methods for rigorously designing & evaluating human-AI workflows?

I'm recruiting PhDs to work on:
🎯 Stat foundations of multi-agent collaboration
🌫️ Model uncertainty & meta-cognition
🔎 Interpretability
💬 LLMs in behavioral science

I’m recruiting students this upcoming cycle at UIUC! I’m excited about Qs on societal impact of AI, especially human-AI collaboration, multi-agent interactions, incentives in data sharing, and AI policy/regulation (all from both a theoretical and applied lens). Apply through CS & select my name!

The ‘Worst Test in Medicine’ is Driving America’s High C-Section Rate

if you think about AI, healthcare, women's health, or all of the above, i highly recommend this article on the role of fetal heart rate monitors in the rise of C-sections:

www.nytimes.com/2025/11/06/h...

Super cool, and something I wish existed within machine learning for healthcare too! I'm often wondering what people are actually doing in practice and assembling evidence for my guesses.

Cornell (NYC and Ithaca) is recruiting AI postdocs, apply by Nov 20, 2025! If you're interested in working with me on technical approaches to responsible AI (e.g., personalization, fairness), please email me.

academicjobsonline.org/ajo/jobs/30971

@michelleding.bsky.social has been doing amazing work laying out the complex landscape of "deepfake porn" and distilling the unique challenges in governing it. We hope this work informs future AI governance efforts to address the severe harms of this content - reach out to us to chat more!

p.s. we pronounce SSME as "Sesame" but you're welcome to your favorite pronunciation :)

Thanks also to our wonderful set of co-authors - Manish Raghavan (@manishraghav.bsky.social) , John Guttag, Bonnie Berger, and Emma Pierson (@emmapierson.bsky.social)-- without whom this work would not be possible!

Last but not least, thanks to @shuvoms.bsky.social,
who co-led this work with me, and is an excellent thinking partner. Collaborate with him if you can!!

The paper includes much more, including theoretical connections to the literature on semi-supervised mixture models. Lots of exciting directions ahead – come chat with me and Shuvom at NeurIPS this December in San Diego!
📄 Paper: arxiv.org/abs/2501.11866
💻 Code: github.com/divyashan/SSME

Across 8 tasks, 4 metrics, and dozens of classifiers, SSME consistently outperforms prior work, reducing estimation error by 5.1× vs. using labeled data alone and 2.4× vs. the next-best method!

SSME starts with a set of classifiers, unlabeled data, and bit of labeled data, and estimates the joint distribution of classifier scores and ground truth labels using a mixture model. SSME benefits from three sources of info: multiple classifiers, unlabeled data, and classifier scores.

New #NeurIPS2025 paper: how should we evaluate machine learning models without a large, labeled dataset? We introduce Semi-Supervised Model Evaluation (SSME), which uses labeled and unlabeled data to estimate performance! We find SSME is far more accurate than standard methods.

thank you, gabriel!! glad i've gotten to learn so much about maps from you :')

thank you, Erica 🥹 so glad we got to work together this year!

thank you, Emma!!! likewise, i'm so grateful for our collaborations over the years!

thank you, Kenny!!! that's so nice of you to say.