Adina Williams
@adinawilliams.bsky.social
NLP, Linguistics, Cognitive Science, AI, ML, etc.
Job currently: Research Scientist (NYC)
Job formerly: NYU Linguistics, MSU Linguistics
Job currently: Research Scientist (NYC)
Job formerly: NYU Linguistics, MSU Linguistics
Reposted by Adina Williams
🌟 New Paper Alert: EvalCards 🌟
Excited to share our new paper, “EvalCards: A Framework for Standardized Evaluation Reporting”is accepted for presentation at the @EurIPSConf workshop on "The Science of Benchmarking and Evaluating AI" .
Excited to share our new paper, “EvalCards: A Framework for Standardized Evaluation Reporting”is accepted for presentation at the @EurIPSConf workshop on "The Science of Benchmarking and Evaluating AI" .
November 13, 2025 at 4:08 PM
🌟 New Paper Alert: EvalCards 🌟
Excited to share our new paper, “EvalCards: A Framework for Standardized Evaluation Reporting”is accepted for presentation at the @EurIPSConf workshop on "The Science of Benchmarking and Evaluating AI" .
Excited to share our new paper, “EvalCards: A Framework for Standardized Evaluation Reporting”is accepted for presentation at the @EurIPSConf workshop on "The Science of Benchmarking and Evaluating AI" .
Reposted by Adina Williams
New work to appear @ TACL!
Language models (LMs) are remarkably good at generating novel well-formed sentences, leading to claims that they have mastered grammar.
Yet they often assign higher probability to ungrammatical strings than to grammatical strings.
How can both things be true? 🧵👇
Language models (LMs) are remarkably good at generating novel well-formed sentences, leading to claims that they have mastered grammar.
Yet they often assign higher probability to ungrammatical strings than to grammatical strings.
How can both things be true? 🧵👇
November 10, 2025 at 10:11 PM
New work to appear @ TACL!
Language models (LMs) are remarkably good at generating novel well-formed sentences, leading to claims that they have mastered grammar.
Yet they often assign higher probability to ungrammatical strings than to grammatical strings.
How can both things be true? 🧵👇
Language models (LMs) are remarkably good at generating novel well-formed sentences, leading to claims that they have mastered grammar.
Yet they often assign higher probability to ungrammatical strings than to grammatical strings.
How can both things be true? 🧵👇
Reposted by Adina Williams
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 RT for reach :)
We're surveying researchers about name changes in academic publishing.
If you've changed your name and dealt with updating publications, we want to hear your experience. Any reason counts: transition, marriage, cultural reasons, etc.
forms.cloud.microsoft/e/E0XXBmZdEP
If you've changed your name and dealt with updating publications, we want to hear your experience. Any reason counts: transition, marriage, cultural reasons, etc.
forms.cloud.microsoft/e/E0XXBmZdEP
November 10, 2025 at 3:11 PM
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 RT for reach :)
Reposted by Adina Williams
UT Austin Linguistics is hiring in computational linguistics!
Asst or Assoc.
We have a thriving group sites.utexas.edu/compling/ and a long proud history in the space. (For instance, fun fact, Jeff Elman was a UT Austin Linguistics Ph.D.)
faculty.utexas.edu/career/170793
🤘
Asst or Assoc.
We have a thriving group sites.utexas.edu/compling/ and a long proud history in the space. (For instance, fun fact, Jeff Elman was a UT Austin Linguistics Ph.D.)
faculty.utexas.edu/career/170793
🤘
UT Austin Computational Linguistics Research Group – Humans processing computers processing humans processing language
sites.utexas.edu
October 7, 2025 at 8:53 PM
UT Austin Linguistics is hiring in computational linguistics!
Asst or Assoc.
We have a thriving group sites.utexas.edu/compling/ and a long proud history in the space. (For instance, fun fact, Jeff Elman was a UT Austin Linguistics Ph.D.)
faculty.utexas.edu/career/170793
🤘
Asst or Assoc.
We have a thriving group sites.utexas.edu/compling/ and a long proud history in the space. (For instance, fun fact, Jeff Elman was a UT Austin Linguistics Ph.D.)
faculty.utexas.edu/career/170793
🤘
Reposted by Adina Williams
We wrote a thing about AI, fascism, and why framing this as "hype" is too apolitical
www.liberalcurrents.com/deflating-hy...
www.liberalcurrents.com/deflating-hy...
Deflating “Hype” Won’t Save Us
The problem with AI isn’t hype. The problem is who and what it’s useful for.
www.liberalcurrents.com
September 16, 2025 at 1:31 PM
We wrote a thing about AI, fascism, and why framing this as "hype" is too apolitical
www.liberalcurrents.com/deflating-hy...
www.liberalcurrents.com/deflating-hy...
Our team is hiring a postdoc in (mechanistic) interpretability! The ideal candidate will have research experience in interpretability for text and/or image generation models and be excited about open science!
Please consider applying or sharing with colleagues: metacareers.com/jobs/2223953961352324
Please consider applying or sharing with colleagues: metacareers.com/jobs/2223953961352324
careers.com
July 15, 2025 at 8:11 PM
Our team is hiring a postdoc in (mechanistic) interpretability! The ideal candidate will have research experience in interpretability for text and/or image generation models and be excited about open science!
Please consider applying or sharing with colleagues: metacareers.com/jobs/2223953961352324
Please consider applying or sharing with colleagues: metacareers.com/jobs/2223953961352324
Reposted by Adina Williams
Ingeborg and I wrote a thing about "hype", and why we think that framing AI through that lens is increasingly inadequate - check it out!
Deflating “Hype” Won’t Save Us
By Hagen Blix & Ingeborg Glimmer
hagenblix.github.io
July 3, 2025 at 8:12 PM
Ingeborg and I wrote a thing about "hype", and why we think that framing AI through that lens is increasingly inadequate - check it out!
Reposted by Adina Williams
Have you heard about this year's shared task? 📢
Mechanistic Interpretability (MI) is quickly advancing, but comparing methods remains a challenge. This year at #BlackboxNLP, we're introducing a shared task to rigorously evaluate MI methods in language models 🧵
Mechanistic Interpretability (MI) is quickly advancing, but comparing methods remains a challenge. This year at #BlackboxNLP, we're introducing a shared task to rigorously evaluate MI methods in language models 🧵
June 23, 2025 at 2:46 PM
Have you heard about this year's shared task? 📢
Mechanistic Interpretability (MI) is quickly advancing, but comparing methods remains a challenge. This year at #BlackboxNLP, we're introducing a shared task to rigorously evaluate MI methods in language models 🧵
Mechanistic Interpretability (MI) is quickly advancing, but comparing methods remains a challenge. This year at #BlackboxNLP, we're introducing a shared task to rigorously evaluate MI methods in language models 🧵
Excited to share the IntPhys 2.0 benchmark for intuitive physics understanding of video! It's super challenging for models but not humans, making it a great testbed for pushing modeling improvements.
Check it out: ai.meta.com/research/pub...
Check it out: ai.meta.com/research/pub...
IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments | Research - AI at Meta
We present IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models. Building on the original...
ai.meta.com
June 12, 2025 at 2:28 PM
Excited to share the IntPhys 2.0 benchmark for intuitive physics understanding of video! It's super challenging for models but not humans, making it a great testbed for pushing modeling improvements.
Check it out: ai.meta.com/research/pub...
Check it out: ai.meta.com/research/pub...
Come by to our panel at APS to share your thoughts, and ask us all the hard stuff!
At APS in DC, thrilled to be moderating a panel on statistics and abstraction in cognition with 3 stars: Jay McClelland, Tom Griffiths @cocoscilab.bsky.social, and @adinawilliams.bsky.social at 1pm tmrw. Bayes. Neural nets. Linguistics…we’ll have it all! www.psychologicalscience.org/conventions/...
2025 Preliminary Program
This preliminary program does not include all sessions and will be updated as additional program information is received. Please check back for the latest program updates. You may also view program in...
www.psychologicalscience.org
May 24, 2025 at 1:10 PM
Come by to our panel at APS to share your thoughts, and ask us all the hard stuff!
Check it out! Guy et al. explores the impact of format on function vectors, and invites further conversation about what it would mean to have universal goal representations in LLMs.
(I've hung around interp communities for a while but this is my 1st mech-interp project. feedback much appreciated!)
(I've hung around interp communities for a while but this is my 1st mech-interp project. feedback much appreciated!)
New preprint alert! We often prompt ICL tasks using either demonstrations or instructions. How much does the form of the prompt matter to the task representation formed by a language model? Stick around to find out 1/N
May 23, 2025 at 5:53 PM
Check it out! Guy et al. explores the impact of format on function vectors, and invites further conversation about what it would mean to have universal goal representations in LLMs.
(I've hung around interp communities for a while but this is my 1st mech-interp project. feedback much appreciated!)
(I've hung around interp communities for a while but this is my 1st mech-interp project. feedback much appreciated!)
COLM 2025 workshops are announced now, check it out: colmweb.org/Workshops.html
COLM 2025: Workshops
colmweb.org
May 20, 2025 at 4:58 PM
COLM 2025 workshops are announced now, check it out: colmweb.org/Workshops.html
Reposted by Adina Williams
Pls come to my book launch on May 22, 5pm, at Newnham College Cambridge cohosted w @mctd.bsky.social and @cfi-cambridge.bsky.social and with stellar discussants @gsvoss.bsky.social and Jennifer Schooling Register here: lu.ma/9vm405sk
Book Launch: Auto-Correct: The Fantasies and Failures of AI, Ethics, and the Driverless Car · Luma
A conversation with Maya Indira Ganesh on how driverless cars are reshaping governance, responsibility, and values
What can a driverless car tell us about…
lu.ma
May 9, 2025 at 1:37 PM
Pls come to my book launch on May 22, 5pm, at Newnham College Cambridge cohosted w @mctd.bsky.social and @cfi-cambridge.bsky.social and with stellar discussants @gsvoss.bsky.social and Jennifer Schooling Register here: lu.ma/9vm405sk
This is such a fun example of LM weirdness (which also shows how they match form over fact!)
More linguistically: it looks like ending a query with "meaning" triggers the bot to accommodate the presupposition that the input contains an idiom! (Hard to run normal preposition tests here tho)
More linguistically: it looks like ending a query with "meaning" triggers the bot to accommodate the presupposition that the input contains an idiom! (Hard to run normal preposition tests here tho)
Someone on Threads noticed you can type any random sentence into Google, then add “meaning” afterwards, and you’ll get an AI explanation of a famous idiom or phrase you just made up. Here is mine
April 23, 2025 at 9:03 PM
This is such a fun example of LM weirdness (which also shows how they match form over fact!)
More linguistically: it looks like ending a query with "meaning" triggers the bot to accommodate the presupposition that the input contains an idiom! (Hard to run normal preposition tests here tho)
More linguistically: it looks like ending a query with "meaning" triggers the bot to accommodate the presupposition that the input contains an idiom! (Hard to run normal preposition tests here tho)
Happy to be at CUNY today to workshop about the theoretical foundations of AI! Fun to have several perspectives---math, philosophy, linguistics and more---together in one place!
w/@giannig.bsky.social @seiller.bsky.social J. Terilla et al.
itsatcuny.org/calendar/202...
w/@giannig.bsky.social @seiller.bsky.social J. Terilla et al.
itsatcuny.org/calendar/202...
Foundations of AI — Initiative for the Theoretical Sciences
Friday, 11 April 9:30 AM - 4:00 PM Rooms 9206/9207, Graduate Center CUNY Join us at the Initiative for Theoretical Sciences for an interdisciplinary exploration of the foundations of artificial i...
itsatcuny.org
April 11, 2025 at 2:15 PM
Happy to be at CUNY today to workshop about the theoretical foundations of AI! Fun to have several perspectives---math, philosophy, linguistics and more---together in one place!
w/@giannig.bsky.social @seiller.bsky.social J. Terilla et al.
itsatcuny.org/calendar/202...
w/@giannig.bsky.social @seiller.bsky.social J. Terilla et al.
itsatcuny.org/calendar/202...
Happy to share that the paper describing the AILuminate v1.0 benchmark is now out! arxiv.org/abs/2503.05731
The benchmark is designed with @mlcommons.org to assess LLM risk and reliability across 12 hazard categories. AILuminate is available for testing models and helping ensure safer deployment!
The benchmark is designed with @mlcommons.org to assess LLM risk and reliability across 12 hazard categories. AILuminate is available for testing models and helping ensure safer deployment!
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standa...
arxiv.org
March 12, 2025 at 2:50 PM
Happy to share that the paper describing the AILuminate v1.0 benchmark is now out! arxiv.org/abs/2503.05731
The benchmark is designed with @mlcommons.org to assess LLM risk and reliability across 12 hazard categories. AILuminate is available for testing models and helping ensure safer deployment!
The benchmark is designed with @mlcommons.org to assess LLM risk and reliability across 12 hazard categories. AILuminate is available for testing models and helping ensure safer deployment!
Reposted by Adina Williams
Our book "Why We Fear AI" is out today! Hopefully it can help make sense out of some of the terrifying stuff that's happening these days, and what AI and capitalism have to do with it!
Get it directly from the publisher or wherever you get your books!
www.commonnotions.org/why-we-fear-ai
Get it directly from the publisher or wherever you get your books!
www.commonnotions.org/why-we-fear-ai
Why We Fear AI — Common Notions Press
www.commonnotions.org
March 11, 2025 at 2:15 PM
Our book "Why We Fear AI" is out today! Hopefully it can help make sense out of some of the terrifying stuff that's happening these days, and what AI and capitalism have to do with it!
Get it directly from the publisher or wherever you get your books!
www.commonnotions.org/why-we-fear-ai
Get it directly from the publisher or wherever you get your books!
www.commonnotions.org/why-we-fear-ai
Reposted by Adina Williams
WHY WE FEAR AI is out today!
Industry insiders @hagenblix.bsky.social and Ingeborg Glimmer dive into the dark, twisted world of AI to demystify the many nightmares we have about it. One of the best ways to face your fear is to confront it—order a copy of WHY WE FEAR AI: buff.ly/1tWhkx8
Industry insiders @hagenblix.bsky.social and Ingeborg Glimmer dive into the dark, twisted world of AI to demystify the many nightmares we have about it. One of the best ways to face your fear is to confront it—order a copy of WHY WE FEAR AI: buff.ly/1tWhkx8
March 11, 2025 at 9:00 AM
WHY WE FEAR AI is out today!
Industry insiders @hagenblix.bsky.social and Ingeborg Glimmer dive into the dark, twisted world of AI to demystify the many nightmares we have about it. One of the best ways to face your fear is to confront it—order a copy of WHY WE FEAR AI: buff.ly/1tWhkx8
Industry insiders @hagenblix.bsky.social and Ingeborg Glimmer dive into the dark, twisted world of AI to demystify the many nightmares we have about it. One of the best ways to face your fear is to confront it—order a copy of WHY WE FEAR AI: buff.ly/1tWhkx8
Reposted by Adina Williams
Why Official English is a terrible idea for the United States, from @lingsocam.bsky.social. Like and share! www.lsadc.org/content.asp?...
LSA
Four Reasons English Should Not be the Official Language: Statement Against White House Executive Order Designating English as the Official Language of The Un
www.lsadc.org
March 6, 2025 at 8:23 PM
Why Official English is a terrible idea for the United States, from @lingsocam.bsky.social. Like and share! www.lsadc.org/content.asp?...
Reposted by Adina Williams
I just interviewed @hagenblix.bsky.social for The Data Fix (episode out early April) and my mind is blown.
Please go buy their book:
www.amazon.ca/gp/product/1...
Please go buy their book:
www.amazon.ca/gp/product/1...
Why We Fear AI: On the Interpretation of Nightmares
Why We Fear AI: On the Interpretation of Nightmares: Blix, Hagen, Glimmer, Ingeborg: 9781945335174: Books - Amazon.ca
www.amazon.ca
March 5, 2025 at 6:06 PM
I just interviewed @hagenblix.bsky.social for The Data Fix (episode out early April) and my mind is blown.
Please go buy their book:
www.amazon.ca/gp/product/1...
Please go buy their book:
www.amazon.ca/gp/product/1...
My spouse co-wrote a book!
It's about AI and what peoples' fears about it actually mean.
Go check it out 👇
It's about AI and what peoples' fears about it actually mean.
Go check it out 👇
Wow, authors' copies have just arrived! So cool (and kinda strange lol) to see our work in print!
Amazing job from @commonnotions.bsky.social! Love the cover design from Josh MacPhee <3
Get a copy here:
www.commonnotions.org/why-we-fear-ai
Amazing job from @commonnotions.bsky.social! Love the cover design from Josh MacPhee <3
Get a copy here:
www.commonnotions.org/why-we-fear-ai
February 15, 2025 at 9:49 PM
My spouse co-wrote a book!
It's about AI and what peoples' fears about it actually mean.
Go check it out 👇
It's about AI and what peoples' fears about it actually mean.
Go check it out 👇
Reposted by Adina Williams
Two new studies from our team we're particularly happy about:
Study 1: ai.meta.com/research/pub...
Study 2: ai.meta.com/research/pub...
Blog 3: ai.meta.com/blog/brain-a...
Study 1: ai.meta.com/research/pub...
Study 2: ai.meta.com/research/pub...
Blog 3: ai.meta.com/blog/brain-a...
February 7, 2025 at 4:17 PM
Two new studies from our team we're particularly happy about:
Study 1: ai.meta.com/research/pub...
Study 2: ai.meta.com/research/pub...
Blog 3: ai.meta.com/blog/brain-a...
Study 1: ai.meta.com/research/pub...
Study 2: ai.meta.com/research/pub...
Blog 3: ai.meta.com/blog/brain-a...
We had two papers accepted at NAACL'25! 🥳
- Improving model evaluation using SMART filtering of benchmark datasets (Gupta et al. arxiv.org/pdf/2410.20245)
- On the role of speech data in reducing toxicity detection bias (Bell et al. arxiv.org/pdf/2411.08135)
- Improving model evaluation using SMART filtering of benchmark datasets (Gupta et al. arxiv.org/pdf/2410.20245)
- On the role of speech data in reducing toxicity detection bias (Bell et al. arxiv.org/pdf/2411.08135)
arxiv.org
January 26, 2025 at 4:19 PM
We had two papers accepted at NAACL'25! 🥳
- Improving model evaluation using SMART filtering of benchmark datasets (Gupta et al. arxiv.org/pdf/2410.20245)
- On the role of speech data in reducing toxicity detection bias (Bell et al. arxiv.org/pdf/2411.08135)
- Improving model evaluation using SMART filtering of benchmark datasets (Gupta et al. arxiv.org/pdf/2410.20245)
- On the role of speech data in reducing toxicity detection bias (Bell et al. arxiv.org/pdf/2411.08135)
My spouse co-wrote a book about AI! Of course, I'm biased, but I think there's a TON of thought provoking stuff inside. Check it out/preorder 👇
I wrote a book about AI, AI Fears, and Capitalism with my friend Ingeborg!
"Why We Fear AI" just went to the printers and comes out in March! You can pre-order it directly at the publisher @commonnotions.bsky.social or wherever you get your books
Quick🧵
"Why We Fear AI" just went to the printers and comes out in March! You can pre-order it directly at the publisher @commonnotions.bsky.social or wherever you get your books
Quick🧵
Why We Fear AI — Common Notions Press
www.commonnotions.org
January 17, 2025 at 2:53 PM
My spouse co-wrote a book about AI! Of course, I'm biased, but I think there's a TON of thought provoking stuff inside. Check it out/preorder 👇
Another post #LSA2025 thought: what's going on linguistically with "at scale" ("at a large enough scale for XYZ").
And maybe it's generalizing? "implement [AI] safely as they move at pace” www.theguardian.com/politics/2025/jan/12/mainlined-into-uks-veins-labour-announces-huge-public-rollout-of-ai
And maybe it's generalizing? "implement [AI] safely as they move at pace” www.theguardian.com/politics/2025/jan/12/mainlined-into-uks-veins-labour-announces-huge-public-rollout-of-ai
‘Mainlined into UK’s veins’: Labour announces huge public rollout of AI
Plans to make UK world leader in AI sector include opening access to NHS and other public data
www.theguardian.com
January 13, 2025 at 2:04 PM
Another post #LSA2025 thought: what's going on linguistically with "at scale" ("at a large enough scale for XYZ").
And maybe it's generalizing? "implement [AI] safely as they move at pace” www.theguardian.com/politics/2025/jan/12/mainlined-into-uks-veins-labour-announces-huge-public-rollout-of-ai
And maybe it's generalizing? "implement [AI] safely as they move at pace” www.theguardian.com/politics/2025/jan/12/mainlined-into-uks-veins-labour-announces-huge-public-rollout-of-ai