Arjun Subramonian (they_them)

3. I will be on a EvalEval panel about sociotechnical perspectives & implications for AI evaluations on 12/8 from 11:00 am - 12:15 pm: evalevalai.com/events/works....

2. My research mentee from UCLA Margaret Capetz will present her work on the fairness of MLPs distilled from GNNs at the Reliable ML workshop on 12/6 from 1:30 pm-2:15 pm: openreview.net/forum?id=6LP....

...

1. @jennmickel.bsky.social and I will present @queerinai.com's AI policy work at the Algorithmic Collective Action workshop on 12/6 from 10:20 am-12:15 pm: openreview.net/forum?id=XvK....

...

I'll be in San Diego for #NeurIPS2025 and EvalEval 12/6-12/8! Let me know if you're around 😊

I unfortunately will not be around for the @queerinai.com workshop and social this year but I will be at the following workshops:

🧵

Please respond to this survey if you have changed or have thought about changing your name in academic publishing! For any reason, whether it be transition, recognizability, marriage, privacy, immigration, cultural reasons, etc.

Please RT for reach :)

Please take 5-10 minutes to fill out this survey!

CW: misgendering

If you're at COLM next week, come say hi to me and @dippedrusk.com at Poster Session 3 on Wednesday morning (Poster #41)! Chat with us about probability-based vs. generation-based LLM evaluations, LLM misgendering, and @queerinai.com 😊

Accepted to #COLM2025! See you in MTL :)

Agree to Disagree? A Meta-Evaluation of LLM Misgendering Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with aut...

Have you or a loved one been misgendered by an LLM? How can we evaluate LLMs for misgendering? Do different evaluation methods give consistent results?
Check out our preprint led by the newly minted Dr. @arjunsubgraph.bsky.social, and with Preethi Seshadri, Dietrich Klakow, Kai-Wei Chang, Yizhou Sun

Announcing our first workshop keynote!

"Processing Trans Languaging" by Vagrant Gautam @dippedrusk.com at 13:30 - 14:30 MDT on May 4, 2025

Read on for a description of the talk! 🧵

Birds of paradise in the sand on a beach. Tide, sunset, and mountains visible.

Corollary to cow on a beach

Went down a huge rabbit hole last night about how the land on which SF was built was primarily covered in massive shifting sand dunes

felt

I can't advise joining an extra Slack workspace, but you should join the AI 4 Conservation Slack if you're not in it already :) at the very least to get images like the one below

credit: github.com/google/camer...

Culture is not trivia: sociocultural theory for cultural NLP. By Naitian Zhou and David Bamman from the Berkeley School of Information and Isaac L. Bleaman from Berkeley Linguistics.

There's been a lot of work on "culture" in NLP, but not much agreement on what it is.

A position paper by me, @dbamman.bsky.social, and @ibleaman.bsky.social on cultural NLP: what we want, what we have, and how sociocultural linguistics can clarify things.

Website: naitian.org/culture-not-...

1/n

We are still looking for annotators! Please consider helping us out, either via filling out the form or sharing it more broadly 💜 Of course, selected annotators are financially compensated.

View of Golden Gate Bridge from Baker Beach. Cloudy weather, ocean foam, and wet sand are visible.

A walk through the Presidio fixes me more than I would like to admit

Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP Vagrant Gautam, Arjun Subramonian, Anne Lauscher, Os Keyes. Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP). 2024.

Very cool work, and a much-needed follow-up to the OpenAI names study! Would also like to share this work with @dippedrusk.com about the use of personal names in NLP: aclanthology.org/2024.gebnlp-... :)

This day in US xenophobia Today, Feb 19, 2025, is a day to see the sheer inhumanity of US anti-immigrant xenophobia at fever pitch. But today is also the 102 year ann...

Today in xenophobia history: 102 years ago today, all Indian American naturalized US citizens were stripped of their citizenship and property. verylowfrequency.blogspot.com/2025/02/this...

Decorative graphic for call for contributions. Graphic reads: "We're seeking research papers, extended abstracts, position papers, opinion pieces, surveys, or media pieces for Queer in AI Workshop at NAACL 2025! Topic of Intrest: Queer Issues in NLP and Linguistics"

🚨 FINAL REMINDER 🚨

Whether you're exploring queer linguistics/NLP or queer activism/D&I, the Queer in AI workshop at #NAACL2025 is the place to be!

📅 Submission Deadline: *Feb 20, 2025 AoE*

Let’s make #NAACL2025 the queerest one yet!
All details 👉 queerinai.com/naacl-2025

#QueerInAI #NLProc

Friendly reminder that all submissions are due Feb 20! Get your submissions in :)

We do have a non-archival track! So do not hesitate to send in your work that is in submission/accepted elsewhere if you are looking for a wonderful group of folks to present your work to

www.queerinai.com/naacl-2025

Oakland dance group performs in halftime show with Kendrick Lamar A dance group from Oakland performed in the half-time show with Kendrick Lamar.

Incredible! 💃🏾🔥 I was so inspired by Oakland’s own TurfFeinz shining on the Super Bowl stage with Kendrick Lamar!

Proud to see our city’s talent on full display. Keep dancing, keep thriving! 🙌🏾✨ #SuperBowlLIX #TurfFeinz

🔗 ktvu.com/news/oakland-dance-group-performs-halftime-show-kendrick-lamar

my reaction exactly 😭

Our workshop has been extended till Feb 20. We are looking forward for your papers at NAACL's Queer in AI workshop.

The archival deadline has been extended to Feb 20! All submissions are now due on Feb 20. Get your work in soon 💜

Beach and tree atop a bluff, clear sky

View of rocks descending into ocean from atop bluff, sunset visible to the side

So UCSB offers free Overleaf and this ??

NAACL 2025 Queer in AI Call for reviewers We are looking for reviewers to review the upcoming submissions to Queer in AI workshop. Each person will get around 1-2 papers to review. Review starts: February 10 Review ends: March 1 Topics wil...

We are looking for reviewers for our Queer in AI NAACL workshop. The reviewing workload is low (1-2 papers) and you will be given ample time to review.

If you are new to reviewing, you are highly encouraged to sign up as a reviewer!

Sign up here: docs.google.com/forms/d/e/1F...

Friendly reminder, the archival deadline is Jan 30 💜

TIL that half of the UCs provide their students with free Overleaf premium, and I am not in that half

View of Pacific Ocean and rolling hills from ridge of Santa Cruz mountains

Never an unpretty day at Russian Ridge