Emma Pierson

Postdoctoral Employee - Artificial Intelligence - Electrical Engineering and Computer Sciences Department University of California, Berkeley is hiring. Apply now!

Apply here - aprecruit.berkeley.edu/JPF05028 by 11/15, but review of applications is ongoing so sooner is better! (Application deadline currently says 9/15 but will be extended).

Sparse Autoencoders for Hypothesis Generation We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a ...

Broad project areas include:

1) language modelling methods for scientific discovery (building on our recent work - arxiv.org/abs/2502.04382)

2) using language models to support equity (ai.nejm.org/doi/full/10....)

both in collaboration with health+social scientists.

2/3

🚨 New postdoc position in our lab at Berkeley EECS! 🚨

(please reshare)

We seek applicants with experience in language modeling who are excited about high-impact applications in the health and social sciences!

More info in thread

1/3

📢New POSITION PAPER: Use Sparse Autoencoders to Discover Unknown Concepts, Not to Act on Known Concepts

Despite recent results, SAEs aren't dead! They can still be useful to mech interp, and also much more broadly: across FAccT, computational social science, and ML4H. 🧵

SF fog coming up to swallow us in time lapse.

Honored to win a #CHIL2025 best paper award for our work modeling inequality in disease progression, led by @ericachiang.bsky.social!

To the NIH: health inequality remains a vital topic to support the health of all Americans. As we prove, failing to account for it biases estimates for everyone.

For folks at @facct.bsky.social, our very own @cornellbowers.bsky.social student @emmharv.bsky.social will present the Best-Paper-Award-winning work she led on Wednesday at 10:45 AM in the "Audit and Evaluation Approaches" session!

In the meantime, 🧵 below and 🔗 here: arxiv.org/abs/2506.04419 !

assassinations, handcuffing a senator at press conference, marines detaining a civilian, and a military parade for the president’s birthday. rough week for democracy.

and... here is the actual GIF 🙈

The first paper of @ericachiang.bsky.social's PhD, just accepted at #CHIL2025, proposes a model of disease progression which estimates and accounts for 3 types of health disparities to more accurately measure disease severity. See her full thread below!

Thanks, Megan!! This is kind :) hope you’re doing well.

My ‘woke DEI’ grant has been flagged for scrutiny. Where do I go from here? My work in making artificial intelligence fair has been noticed by US officials intent on ending ‘class warfare propaganda’.

The US government recently flagged my scientific grant in its "woke DEI database". Many people have asked me what I will do.

My answer today in Nature.

We will not be cowed. We will keep using AI to build a fairer, healthier world.

www.nature.com/articles/d41...

A pleasure to join the Tech Policy Press podcast with @natematias.bsky.social, @geomblog.bsky.social, and @justinhendrix.bsky.social to defend the consensus that AI bias is an important concern.

Lab had dogathon! Seminal dog discoveries ensued.

This work is led by @gsagostini.bsky.social, who gets more excited about geospatial data than anyone I've ever met, and with Rachel Young, Maria Fitzpatrick, and @nkgarg.bsky.social.

Paper: arxiv.org/abs/2503.20989
Website (and data): migrate.tech.cornell.edu
Thread: bsky.app/profile/gsag...

Migration data is critical in the health, environmental, and social sciences.

We're releasing a new dataset, MIGRATE: annual flows between 47 billion pairs of US Census areas. MIGRATE is:

- 4600x more granular than existing public data
- highly correlated with external ground-truth data

1/2

💡New preprint & Python package: We use sparse autoencoders to generate hypotheses from large text datasets.

Our method, HypotheSAEs, produces interpretable text features that predict a target variable, e.g. features in news headlines that predict engagement. 🧵1/

This work is led by the wonderful @rajmovva.bsky.social and @kennypeng.bsky.social with coauthors @nkgarg.bsky.social and Jon Kleinberg. See Raj’s full thread for details, Python package, and project website!

bsky.app/profile/rajm...

HypotheSAEs outperforms strong LLM baselines, generates new discoveries even on well-studied datasets, and comes with easy-to-use code.

We hope this will be helpful not just to CS folks, but to many in social/health sciences - please reshare to help reach them.

We have a new method, HypotheSAEs, for identifying *interpretable text features that predict a target variable* (aka hypothesis generation).

What features of a headline predict engagement?

What features of a clinical note predict whether a patient will develop cancer?

1/

Humbled and honored to receive this award -- thank you, @sloanfoundation.bsky.social, for supporting STEM research!

Machine Learning in Economics Summer Institute 2025 (MLESI25) <span id="docs-internal-guid-53f97f20-7fff-b55c-c89c-4f85d663a48c" style="color: #39393a;"><span style="color: #000000;">MLESI<span id="docs-internal-guid-394e21c4-7fff-1437-16ff-fdbb1ce1d34c" style="...

Applications are open for the Machine Learning in Economics Summer Institute (MLESI) 2025 are open!

If you're a graduate student, come learn about ML/AI and its uses throughout economics.

Apply by March 28. The application and more info can be found here: www.chicagobooth.edu/research/cen...

In general, we're certainly not claiming philanthropists can or should fully replace federal funding (for the reasons you point out!)

Rather, we're arguing that philanthropists should consider which areas have been particularly hard-hit by rash federal funding cuts when they decide what to fund.

I totally agree about the importance of federal funding!! It will be a great loss if it is severely cut.

New piece in Nature: @leahpierson.bsky.social and I argue that philanthropic funders should shield science from cuts the Trump administration may make to climate science, infectious disease, etc.

Free access link: rdcu.be/d6aul
Longer version on my website: shorturl.at/muwts

...@sendhil.bsky.social, Ziad Obermeyer, @harinisuresh.bsky.social, and @keyonv.bsky.social!

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...

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.

Oregon stars. Happy holidays to all!

Some holiday reading if you're looking for an accessible, up-to-date overview of the fast-moving generative AI in medicine literature - our new paper, to appear in Annual Review of Biomedical Data Science!