If you're at #ICML2025, chat with me, @sarah-nlp.bsky.social, Atticus, and others at our poster 11am - 1:30pm at East #1205! We're establishing a ๐ echanistic ๐nterpretability ๐enchmark.
We're planning to keep this a living benchmark; come by and share your ideas/hot takes!
17.07.2025 17:45 โ ๐ 13 ๐ 3 ๐ฌ 0 ๐ 0
I am also recruiting PhD students @univofmaryland.bsky.social for fall 2026 with interests in (causal/mechanistic) LM interpretability and its practical applications (steering, efficient adaptation, model editing, textual explanations for users, etc.).
16.07.2025 23:09 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
I am at #ICML2025! ๐จ๐ฆ๐๏ธ
Catch me:
1๏ธโฃ Presenting this paper๐ tomorrow 11am-1:30pm at East #1205
2๏ธโฃ At the Actionable Interpretability @actinterp.bsky.social workshop on Saturday in East Ballroom A (Iโm an organizer!)
16.07.2025 23:09 โ ๐ 3 ๐ 1 ๐ฌ 1 ๐ 0
This week is #ICML in Vancouver, and a number of our researchers are participating. Here's the full list of Ai2's conference engagementsโwe look forward to connecting with fellow attendees. ๐
14.07.2025 19:30 โ ๐ 3 ๐ 2 ๐ฌ 0 ๐ 0
Thank you! Look forward to being colleagues.
26.06.2025 07:24 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Thank you!
26.06.2025 07:24 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Thank you!
26.06.2025 07:24 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Thanks :))
26.06.2025 07:24 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Thanks so much for all your support โบ๏ธ๐ฅฐ
16.06.2025 22:11 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
Thank you!
16.06.2025 04:11 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Thank you ๐
16.06.2025 04:11 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
โบ๏ธ come visit!
16.06.2025 04:11 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
A bit late to announce, but Iโm excited to share that I'll be starting as an assistant professor at UMD CS @univofmaryland.bsky.social this August.
I'll be recruiting PhD students this upcoming cycle for fall 2026. (And if you're a UMD grad student, sign up for my fall seminar!)
13.06.2025 18:20 โ ๐ 65 ๐ 3 ๐ฌ 13 ๐ 1
Congrats Kristina! ๐
30.05.2025 18:11 โ ๐ 1 ๐ 0 ๐ฌ 1 ๐ 0
An image with the Vancouver skyline and the words "sign up to review". At the top are the logos of both the Actionable Interpretability workshop (a magnifying glass) and the ICML conference (a brain).
๐จ We're looking for more reviewers for the workshop!
๐ Review period: May 24-June 7
If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input.
๐ก๐ Self-nominate here:
docs.google.com/forms/d/e/1F...
20.05.2025 00:05 โ ๐ 6 ๐ 5 ๐ฌ 0 ๐ 0
๐ค: "Great review, but it could be improved by doing [exact thing I wrote in subsequent sentences]"
25.04.2025 02:37 โ ๐ 3 ๐ 0 ๐ฌ 0 ๐ 0
Where is version control and shared editing for keynote files?! ๐คฆโโ๏ธ
25.04.2025 02:36 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
We are quite excited about the leaderboard and release, and are open to feedback to help this remain a living benchmark.
25.04.2025 02:24 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
Checkout our new preprint/project which has been over a year in the making! This has been a very fun collaboration (and one of the biggest I've personally participated in).
@amuuueller.bsky.social @boknilev.bsky.social and other co-authors are around #ICLR2025 if you want to find out more. ๐
25.04.2025 02:24 โ ๐ 9 ๐ 0 ๐ฌ 1 ๐ 0
See Yanai's thread for more info:
bsky.app/profile/yana...
25.04.2025 02:21 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
2) On the connection between linear relational embeddings in LMs and frequency of relations in pretraining data
- Led by @jackmerullo.bsky.social w/ @nlpnoah.bsky.social @yanai.bsky.social
- arxiv.org/abs/2504.12459
- Yanai is presenting the poster tomorrow 04/26 10am-12:30pm (Hall 3+Hall 2B #236)!
25.04.2025 02:20 โ ๐ 2 ๐ 1 ๐ฌ 1 ๐ 1
I'm not at #ICLR2025, but have 2 works being presented:
1) Understanding how LMs answer multiple-choice questions
- arxiv.org/abs/2407.15018
- @boknilev.bsky.social is presenting the poster *now* until 12:30 (Hall 3+Hall 2B #207)
- & w/ @oyvind-t.bsky.social @hanna-nlp.bsky.social Ashish Sabharwal
25.04.2025 02:18 โ ๐ 6 ๐ 1 ๐ฌ 1 ๐ 1
I'm in Singapore for ICLR to present this paper:
Tomorrow, April 26th, 10-12:30 in Hall 3+2B #236
Come check it out!
arxiv.org/abs/2504.12459
25.04.2025 01:55 โ ๐ 3 ๐ 2 ๐ฌ 0 ๐ 0
๐ก New ICLR paper! ๐ก
"On Linear Representations and Pretraining Data Frequency in Language Models":
We provide an explanation for when & why linear representations form in large (or small) language models.
Led by @jackmerullo.bsky.social, w/ @nlpnoah.bsky.social & @sarah-nlp.bsky.social
25.04.2025 01:55 โ ๐ 42 ๐ 12 ๐ฌ 3 ๐ 3
Have work on the actionable impact of interpretability findings? Consider submitting to our Actionable Interpretability workshop at ICML! See below for more info.
Website: actionable-interpretability.github.io
Deadline: May 9
03.04.2025 17:58 โ ๐ 20 ๐ 10 ๐ฌ 0 ๐ 0
๐ข Open PhD Position in Interpretable Natural Language Processing at the Department of Computer Science, UCPH!
๐ Application deadline is 15 January 2025.
Find more information about the position and apply here ๐ di.ku.dk/english/abou...
@apepa.bsky.social @iaugenstein.bsky.social
08.01.2025 10:43 โ ๐ 9 ๐ 2 ๐ฌ 0 ๐ 0
๐คฉ
11.12.2024 21:17 โ ๐ 4 ๐ 0 ๐ฌ 0 ๐ 0
Enjoying my FOMO coffee this morning
08.12.2024 18:39 โ ๐ 36 ๐ 0 ๐ฌ 3 ๐ 0
Ok one thing I sorely need here is bookmarks
26.11.2024 08:06 โ ๐ 21 ๐ 0 ๐ฌ 1 ๐ 0
๐ฏ Making AI less evil= human-centered + explainable + responsible AI
๐ผ Harvard Berkman Klein Fellow | CS Prof. @Northeastern | Data & Society
๐ข Prev-Georgia Tech, {Google, IBM, MSFT}Research
๐ฌ AI, HCI, Philosophy
โ F1, memes
๐ upolehsan.com
PhD Student at @gronlp.bsky.social ๐ฎ, core dev @inseq.org. Interpretability โฉ HCI โฉ #NLProc.
gsarti.com
Modeling Linguistic Variation to expand ownership of NLP tools
Views my own, but affiliations that might influence them:
ML PhD Student under Prof. Diyi Yang
2x RS Intern๐ฆ Pretraining
Alum NYU Abu Dhabi
Burqueรฑo
he/him
Associate Professor of Human-Centered Computing and Social Informatics at Penn State. AI and sociotechnical NLP, especially for privacy and fairness. Also posting about academia, photography, and travel. Opinions mine. he/him. http://shomir.net
Assistant Professor at UCLA. Alum @StanfordNLP. NLP, Cognitive Science, Accessibility. https://www.coalas-lab.com/elisakreiss
UC Davis computational psycholinguist (she)
Assistant professor at University of Pennsylvania. Machine learning, optimization, robustness & interpretability.
Home page: https://www.cis.upenn.edu/~exwong/
Lab page: https://brachiolab.github.io/
Research blog: https://debugml.github.io/
Senior research scientist @ GoogleDeepMind | benchmarking and evaluation | prev @upenn.edu @ai2.bsky.social, and @ltiatcmu.bsky.socialโฌ
chaitanyamalaviya.github.io
Assistant Professor of Computer Science @JohnsHopkins,
CS Postdoc @Stanford,
PHD @EPFL,
Computational Social Science, NLP, AI & Society
https://kristinagligoric.com/
2 Nobel laureates, 6 Pulitzer recipients, scores of Fulbright scholars, one cute turtle and a bike ride away from our nation's capital!
Anti-cynic. Towards a weirder future. Reinforcement Learning, Autonomous Vehicles, transportation systems, the works. Asst. Prof at NYU
https://emerge-lab.github.io
https://www.admonymous.co/eugenevinitsky
Iโm a professor at Cornell Tech and Cornell Law School.
One of "a number of very informative people." -WSJ
Linguist at Georgia Tech (semantics, socio) with my own views; runner with type 1 diabetes; mom of 2
Assistant Professor at @cs.ubc.caโฌ and โช@vectorinstitute.aiโฌ working on Natural Language Processing. Book: https://lostinautomatictranslation.com/
๐ ๏ธ Actionable Interpretability๐ @icmlconf.bsky.social 2025 | Bridging the gap between insights and actions โจ https://actionable-interpretability.github.io
The Language Technologies Institute in Carnegie Mellon University's @scsatcmu.bsky.social
lti.cmu.edu
Prof, Chair for AI & Computational Linguistics,
Head of MaiNLP lab @mainlp.bsky.social, LMU Munich
Co-director CIS @cislmu.bsky.social
Visiting Prof ITU Copenhagen @itu.dk
ELLIS Fellow @ellis.eu
Vice-President ACL
PI MCML @munichcenterml.bsky.social
Stanford Professor of Linguistics and, by courtesy, of Computer Science, and member of @stanfordnlp.bsky.social and The Stanford AI Lab. He/Him/His. https://web.stanford.edu/~cgpotts/