Bingo! Do I win a prize now?

Ever used a top-ranked LLM that just... felt wrong for you? You’re not alone. Instead of leaderboards, many of us turn to "vibe-testing" - manually comparing models to our own needs. But can we turn these feelings into a structured evaluation? New paper: "From Feelings to Metrics" 🧵

We are delighted to welcome @marlutz.bsky.social to our lab over the next few months! 🎉 She'll work on the representation of different demographic groups in LLMs. #NLProc

FYI #ACL2026 has an unusual registration system this year, and probably a lot of people who want to attend will not be able to. Spots are limited to 3.5k people, and only presenting authors can register during the first phase. Then, *if* there are spots left, others can try to register.

📢 The workshop on Insights from negative results will be back at EMNLP'26! Your most-insightful failures can be submitted in 4 pages by June 25. It's also possible to commit short papers reviewed through ARR. insights-workshop.github.io/2026/cfp

How can generative AI better support human creativity, without limiting it? If you have thoughts, we invite submissions to our ICML workshop on Generative AI, Creativity, and Human-AI Co-Creation 📍 July 2026, Seoul 📄 Submit by: April 24 (AOE) 🔗 Submission link: openreview.net/group?id=ICM...

❗The full paper submission deadline for COLM is ~14 hours from now (11:59pm AOE)! Please submit your final PDFs on the same page where you uploaded your abstracts. And please use the provided LaTeX templates; do not handwrite your manuscript like this llama is! Good luck!

Interested in pursuing a PhD in NLP/cog-sci? Studying language learning in LMs from the perspective of human language acquisition? Few more days to apply!!

A piece co-authored by an old friend (Divya Saini, a psychiatrist at Massachusetts General Hospital) www.nytimes.com/2026/03/29/o...

Check out works on sequence repetition 🔁 and evaluating synthetic data 🧮 from our lab in Rabat! @eaclmeeting.bsky.social #EACL2026

To ease my FOMO from not attending @eaclmeeting.bsky.social, I skimmed the proceedings while playing the Tangier episode of Parts Unknown. I'll do something different and shout out 5 (subjectively) interesting works of authors I'm *not* closely related to, in no specific order:🧵⬇️

Thinking of applying for an #MSCA Postdoctoral Fellowship in 2026? I’m open to supervising at Bocconi! Feel free to reach out. By submitting an expression of interest to Bocconi, selected applicants will receive full proposal support. 🗓️ Deadline: April 15 👉 www.unibocconi.it/en/horizon-e...

Excited to present this work together with @dippedrusk.com at #EACL. Join us in the poster session 1 (11:30-13:00) 🔥

Excited to share that @milanlp.bsky.social will be presenting 5 new papers at #EACL2026 and workshops in Rabat 🇲🇦!

Argh this sucks. apparently they lost their funding guarantee

You are #EACL2026? Check out some great work from the CSS Department @gesis.org, our data Science Methods team, with great collaborators!

I’m seeing close to zero reaction/conversation about this on here. This is huge news for open research on language models, especially in the US.

“It’s toddler AI misinformation at an industrial scale. It’s very risky for the developing brain.” Children’s media experts say AI-generated “slop" has infiltrated the internet, preying on young children and their unsuspecting caregivers.

We'll have a reproducibility track at this years' Blackbox workshop! Details are still within a slightly opaque box. We want to see if cleaning solutions that make opaque boxes 📦 transparent 🍱 work on different boxes 🎁📮🧰🥡, and with different 🧽solution-to-water🧼ratios!

How does an LLM’s past influence its future?🤔 In new work, led by @adisimhi.bsky.social, together with @fbarez.bsky.social @boknilev.bsky.social and Shay Cohen, we find conversational history creates a latent "geometric trap" which makes old habits e.g. hallucinations hard to break!

NSF Update through March 13, 2026 1/2

#MemoryModay #NLProc 'Make Natural Language Processing About People Again' by @dirkhovy.bsky.social (2018) uncovers how AI models portray different religions and emotions. #AIEthics

Sharing “Neural Thickets”. We find: In large models, the neighborhood around pretrained weights can become dense with task-improving solutions. In this regime, post-training can be easy; even random guessing works Paper: arxiv.org/abs/2603.12228 Web: thickets.mit.edu 1/

📢 PhD position in Developmental Language Modelling (PLZ RT) What can human language acquisition teach us about training language models? Join us as a PhD! mpi.nl/career-education/vacancies/vacancy/fully-funded-4-year-phd-position-developmental-language @carorowland.bsky.social @mpi-nl.bsky.social

📢 PhD position in the NeuroAI of Language Why can LLMs predict brain activity so well? We're hiring a PhD student to find out -- AI interpretability meets neuroimaging Deadline March 20 Please RT 🙏 👇 mpi.nl/career-education/vacancies/vacancy/fully-funded-4-year-phd-position-neuroai-language

Great test for anyone learning mech interp is reading Nikankin et al's "Arithmetic Without Algorithms" which uses activation patching / circuits, probing, logit lens, describing max activating examples.. If you you follow along while reading, you'll realize you know a lot! arxiv.org/abs/2410.21272

We were thrilled to host @mtutek.bsky.social at our lab last week. His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! 👏 #Transformers #AISafety #ExplainableAI #MLResearch #NLProc

Can LLMs figure out who you are from your anonymous posts? From a handful of comments, LLMs can infer where you live, what you do, and your interests; then search for you on the web. New 📄 w/ @SimonLermenAI, @joshua_swans, @AerniMichael, Nicholas Carlini, @florian_tramer 🧵

Extracting structural/linguistic properties for large text datasets can be annoying. Existing tools either are not maintained, do not scale, or do not cover extensive sets of linguistic features. For this reason, I implemented 🧝elfen, a Python package for efficient linguistic feature extraction

🚨 Emergency reviewer needed for ARR Resources and Evaluation track! Please ping me if you could review one paper by Friday. Topic is AI hallucinations, broadly speaking.

Hello #NLProc #ACL2026NLP people. I am looking for **two emergency reviewers** in the Safety and Alignment in LLMs track for ACL/ARR. Reviews are due Feb 15th. Please DM if interested and available. Happy to offer drinks/food if you live in/pass by Lisbon ☀️

Hello #NLProc #ACL2026NLP community, I'm looking for an emergency reviewer for an ARR submission on LLM interpretability. If you're available to complete a review before Feb 15, please reply or DM 🙏

I need one too!

I could use an emergency reviewer for an ACL submission involving interpretability and syntax. Please DM me if you might be able to provide an emergency review before February 15!

I am looking for 2 emergency reviewers for the ARR Ethics, Bias & Fairness track. Please DM me if you are available 🙏

I'm looking for two emergency reviewers 🧑‍🚒👩‍🚒 for the ARR January Generalizability and Transfer track. Please reach out if you have time & qualify for review or RT for visibility🙏🙏

Seems to be a common situation for ACs this round, but I'm also looking for two emergency reviewers for the January #ARR Evaluation and Resources track. I'd appreciate any help (reposts, encouragement, black magic...)

Looking for emergency reviewers for ARR Special Track "Explainability of NLP Models". Topics: Faithfulness, mechanistic interpretability, surveys and position papers. Deadline Feb 14 AoE. #ACL2026NLP

I'm sorry the guy changing the rules on the fly is named what

We already know prompt repetition is a handy hack to improve a decoder-only LM’s performance as it allows the model to “see” bidirectionally, an ability otherwise suppressed by the causal mask. But what happens if we increase the number of repetitions? 🤔🧵 @eaclmeeting.bsky.social #EACL2026

ManagerBench was accepted to ICLR! @iclr-conf.bsky.social #ICLR2026 LLMs are still either unsafe, or completely harm avoidant - even when the harm affects furniture 🛋️ Check out our benchmark, online or in Rio 🇧🇷

Matija Luka Kuki\'c, Marko \v{C}uljak, David Duki\'c, Martin Tutek, Jan \v{S}najder Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models https://arxiv.org/abs/2601.17585

LMs that "know more" about toxicity are less toxic! Our #TACL 📄 connects behavior and internals: 💠 LMs amplify toxicity beyond humans 💠 Information about toxicity peaks in lower layers 💠 Bypassing these layers increases toxicity More details👇 #NLProc #interpretability (1/🧵)

Can you solve this algebra puzzle? 🧩 cb=c, ac=b, ab=? A small transformer can learn to solve problems like this! And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️

⏳ Deadline approaching! We’re hiring 2 fully funded postdocs in #NLP. Join the MilaNLP team and contribute to our upcoming research projects (SALMON & TOLD) 🔗 Details + how to apply: milanlproc.github.io/open_positio... ⏰ Deadline: Jan 31, 2026

Nathan Stringham, Fateme Hashemi Chaleshtori, Xinyuan Yan, Zhichao Xu, Bei Wang, Ana Marasovi\'c Teaching People LLM's Errors and Getting it Right https://arxiv.org/abs/2512.21422

🚀 We’re opening 2 fully funded postdoc positions in #NLP! Join the MilaNLP team and contribute to our upcoming research projects. 🔗 More details: milanlproc.github.io/open_positio... ⏰ Deadline: Jan 31, 2026

COLM 2026 is just around the corner! Mark your calendars for: 💡 Abstract deadline: Thursday, March 26, 2026 📄 Full paper submission deadline: Tuesday, March 31, 2026 Call for papers (website coming soon): docs.google.com/document/d/1...

At the #Neurips2025 mechanistic interpretability workshop I gave a brief talk about Venetian glassmaking, since I think we face a similar moment in AI research today. Here is a blog post summarizing the talk: davidbau.com/archives/202...

I’m recruiting a postdoc to work on algorithms for cancer genome reconstruction. We have access to a rich set of tumour samples sequenced across multiple technologies. If interested, feel free to DM. Please share.