Sign in

Martin Tutek

@mtutek.bsky.social
371 followers 402 following 95 posts

Postdoc @ TakeLab, University of Zagreb | Working on interpretability & safety of LLMs. mttk.github.io

PostsRepliesMedia
Martin Tutek @mtutek.bsky.social · 09/09/2026
Take a break from reading up on Navier-Stokes drama and add October 29th to your calendar, as we have a stellar lineup of speakers at this years' BlackboxNLP!
051
Reposted by Martin Tutek
BlackboxNLP @blackboxnlp.bsky.social · 31/08/2026
Due to the unprecedented amount of submissions to BlackboxNLP 2026, we will announce the decisions for Main, Special and ARR commitments on September 2 AoE. Thanks for your patience!
063
Martin Tutek @mtutek.bsky.social · 22/08/2026
The @blackboxnlp.bsky.social reproducibility track is in an urgent need for reviewers! If you can review a paper (or two), these bite-sized papers deserve some attention, and reviewing them will leave you fulfilled! 🥰 Please reach out if you can help out! RTs appreciated 👐
035
Reposted by Martin Tutek
Debora Nozza @deboranozza.bsky.social · 07/08/2026
Very happy that #IC2S22027 will be in Milan at Università Bocconi! I’m really looking forward to welcoming the computational social science community to my university and to Milan, and excited to be part of the team organizing it. See you in 2027! 🇮🇹✨
15212
Reposted by Martin Tutek
BlackboxNLP @blackboxnlp.bsky.social · 21/07/2026
With a high volume of submissions this year, we're recruiting additional reviewers for BlackboxNLP 2026! 🗓 Review deadline: August 17 (AoE) 🗓 Review load: 2-4 papers 📝 Sign up: forms.gle/tha166UQZYqX...
065
Reposted by Martin Tutek
MilaNLP Lab @milanlp.bsky.social · 16/07/2026
For today's reading group, @veraneplenbroek.bsky.social presented "Old Habits Die Hard: How Conversational History Geometrically Traps LLMs" by Simhi et al. (2026) Paper: arxiv.org/abs/2603.03308 #NLProc
0125
Reposted by Martin Tutek
BlackboxNLP @blackboxnlp.bsky.social · 16/07/2026
⏳ The BlackboxNLP 2026 Reproducibility Challenge deadline has been extended to July 24 (AoE) ⏳ If you've been working on a robustness check, ablation, or replication of recent NLP interpretability work, you have a bit more time to get your submission in.
186
Reposted by Martin Tutek
BlackboxNLP @blackboxnlp.bsky.social · 11/07/2026
⏳ One week left! The submission deadline for BlackboxNLP 2026 is July 17 (AoE). If you're working on analyzing or interpreting neural networks for NLP, now's the time to get your paper in. 📍 Co-located with #EMNLP2026 in Budapest 🔗 blackboxnlp.github.io
062
Reposted by Martin Tutek
BlackboxNLP @blackboxnlp.bsky.social · 01/07/2026
🏆 Announcing the NDIF Best Paper Award for the BlackboxNLP 2026 Reproducibility Challenge! @ndif-team.bsky.social Reproduce an interp. finding with nnsight + NDIF, open-source it, and push it further. Winners will receive a $500 prize, and will be invited to present at the workshop!
183
Reposted by Martin Tutek
takelab.bsky.social @takelab.bsky.social · 30/06/2026
At ICML '26, TakeLab members are presenting three papers. Make sure to stop by if interested in language model interpretability, coding agent evaluations, or pluralistic alignment. Details below 👇🧵 @icmlconf.bsky.social #ICML2026 🇰🇷
141
Reposted by Martin Tutek
EACL 2027 @eaclmeeting.bsky.social · 30/06/2026
📣 #EACL2027 updates: the Call for Papers is live, and our keynote speakers are confirmed! Main conference: 9–14 March 2027. Special theme: The Human in Language. 🧵👇 2027.eacl.org/calls/papers/
2027.eacl.org
Call for Papers
Official website for the 2027 Conference of the European Chapter of the Association for Computational Linguistics
12113
Reposted by Martin Tutek
Naomi Saphra @nsaphra.bsky.social · 15/06/2026
We don’t always know what problems are hard for LLMs. So devs evaluate on tasks HUMANS find hard or on broad benchmarks. What if we could instead anticipate which scenarios a model will fail on—all without evaluating specific input examples? 🧵NEW PAPER by @jenniferlumeng.bsky.social
313734
Reposted by Martin Tutek
Naomi Saphra @nsaphra.bsky.social · 09/06/2026
✨ it's coming ✨ NEMI 2026 will be lit. It will also be the new BU interp supergroup's debut ball. Come meet us!
nemiconf.github.io
The 3rd New England Mechanistic Interpretability (NEMI) Workshop
1274
Martin Tutek @mtutek.bsky.social · 02/06/2026
With the large influx of submissions and a faster pace of research, reproducibility is more important than ever. With this reproducibility challenge, we want to put the focus on best practices wrt. baselines🧱, ablations🌈, eval🔎 and generalizability🗺️ of interpretability!
073
Reposted by Martin Tutek
BlackboxNLP @blackboxnlp.bsky.social · 28/05/2026
📣 Announcing the BlackboxNLP 2026 Reproducibility Challenge! A new track dedicated to rigorous robustness checks of NLP interpretability work - stress-testing baselines, ablations, generalizability, and evaluation.
1165
Reposted by Martin Tutek
Markus Eichhorn @markuseichhorn.bsky.social · 07/05/2026
Bingo! Do I win a prize now?
Comic strip titles self-sabotaging academic habits that feel normal, featuring nine panels.
1122583
Reposted by Martin Tutek
Itay Itzhak @ COLM 🍁 @itay-itzhak.bsky.social · 23/04/2026
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" 🧵
271
Reposted by Martin Tutek
MilaNLP Lab @milanlp.bsky.social · 21/04/2026
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
0248
Reposted by Martin Tutek
Maria Antoniak @mariaa.bsky.social · 21/04/2026
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.
2026.aclweb.org
Registration
Official website for the 64th Annual Meeting of the Association for Computational Linguistics
2113
Reposted by Martin Tutek
Anna Rogers @annarogers.bsky.social · 13/04/2026
📢 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
insights-workshop.github.io
2026 Call for Papers
Workshop on Insights from Negative Results in NLP
03211
Reposted by Martin Tutek
Abhilasha Ravichander @lasha.bsky.social · 12/04/2026
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...
openreview.net
ICML 2026 Workshop GenAICreativity
Welcome to the OpenReview homepage for ICML 2026 Workshop GenAICreativity
0218
Reposted by Martin Tutek
Conference on Language Modeling @colmweb.org · 31/03/2026
❗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!
A llama sweating while writing a paper at a desk. A sign says "Deadline! March 31 11:59pm AOE"
094
Reposted by Martin Tutek
micha heilbron @mheilbron.bsky.social · 30/03/2026
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!!
071
Reposted by Martin Tutek
Lucy Li @lucy3.bsky.social · 29/03/2026
A piece co-authored by an old friend (Divya Saini, a psychiatrist at Massachusetts General Hospital) www.nytimes.com/2026/03/29/o...
nytimes.com
Opinion | Your Chatbot Isn’t a Therapist
091
Martin Tutek @mtutek.bsky.social · 26/03/2026
Check out works on sequence repetition 🔁 and evaluating synthetic data 🧮 from our lab in Rabat! @eaclmeeting.bsky.social #EACL2026
040
Martin Tutek @mtutek.bsky.social · 25/03/2026
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:🧵⬇️
140
Reposted by Martin Tutek
Debora Nozza @deboranozza.bsky.social · 25/03/2026
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...
unibocconi.it
Horizon Europe - Marie Skłodowska-Curie Actions Postdoctoral Fellowships 2026 - Bocconi University
054
Reposted by Martin Tutek
Andreas Waldis @tresiwald.bsky.social · 25/03/2026
Excited to present this work together with @dippedrusk.com at #EACL. Join us in the poster session 1 (11:30-13:00) 🔥
Poster of the Paper Aligned Probing
041
Reposted by Martin Tutek
MilaNLP Lab @milanlp.bsky.social · 25/03/2026
Excited to share that @milanlp.bsky.social will be presenting 5 new papers at #EACL2026 and workshops in Rabat 🇲🇦!
594
Reposted by Martin Tutek
Naomi Saphra @nsaphra.bsky.social · 24/03/2026
Argh this sucks. apparently they lost their funding guarantee
4163
Reposted by Martin Tutek
Gabriella Lapesa @gabriellalapesa.bsky.social · 24/03/2026
You are #EACL2026? Check out some great work from the CSS Department @gesis.org, our data Science Methods team, with great collaborators!
4124
Reposted by Martin Tutek
Maria Antoniak @mariaa.bsky.social · 24/03/2026
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.
37317
Reposted by Martin Tutek
Mother Jones @motherjones.com · 18/03/2026
“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.
motherjones.com
This is your kid's brain on AI slop
“It’s toddler AI misinformation at an industrial scale. It’s very risky for the developing brain.”
19508158
Martin Tutek @mtutek.bsky.social · 18/03/2026
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!
062
Martin Tutek @mtutek.bsky.social · 17/03/2026
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!
2245
Reposted by Martin Tutek
Jeremy Berg @jeremymberg.bsky.social · 16/03/2026
NSF Update through March 13, 2026 1/2
A line graph of the number of NSF awards in fiscal 2026 compared to fiscal years 2021-2025. The fiscal year 2026 is well below the other curves and increasing only very slowly.
28805390
Reposted by Martin Tutek
MilaNLP Lab @milanlp.bsky.social · 16/03/2026
#MemoryModay #NLProc 'Make Natural Language Processing About People Again' by @dirkhovy.bsky.social (2018) uncovers how AI models portray different religions and emotions. #AIEthics
aclanthology.org
The Social and the Neural Network: How to Make Natural Language Processing about People again
Dirk Hovy. Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media. 2018.
075
Reposted by Martin Tutek
Phillip Isola @phillipisola.bsky.social · 13/03/2026
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/
610823
Reposted by Martin Tutek
micha heilbron @mheilbron.bsky.social · 10/03/2026
📢 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
12935
Reposted by Martin Tutek
micha heilbron @mheilbron.bsky.social · 05/03/2026
📢 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
25239
Reposted by Martin Tutek
Ana Marasović @anamarasovic.bsky.social · 04/03/2026
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
arxiv.org
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmetic reasoning as a rep...
1164
Reposted by Martin Tutek
MilaNLP Lab @milanlp.bsky.social · 24/02/2026
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
0183
Reposted by Martin Tutek
Daniel Paleka @dpaleka.bsky.social · 20/02/2026
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 🧵
812442
Reposted by Martin Tutek
Maximilian Maurer @mmmaurer.bsky.social · 18/02/2026
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
Code examples for the Python package elfen:

# initializing extractor
extractor = elfen.Extractor(
data = df,
language = "en",
text_column = "text")
# extracting a single feature: ttr
extractor.extract("ttr")
# extracting a feature area/group: readability
extractor.extract_feature_group("readability")
# extracting all available features
extractor.extract_features()
1135
Reposted by Martin Tutek
Marcel Bollmann @marcel.bollmann.me · 11/02/2026
🚨 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.
113
Reposted by Martin Tutek
Giuseppe Attanasio @gattanasio.cc · 10/02/2026
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 ☀️
0610
Reposted by Martin Tutek
Shane Storks @shanestorks.bsky.social · 10/02/2026
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 🙏
026
Reposted by Martin Tutek
Jelle Zuidema 🟥 @wzuidema.bsky.social · 10/02/2026
I need one too!
022
Reposted by Martin Tutek
Tom McCoy @rtommccoy.bsky.social · 10/02/2026
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!
144
Reposted by Martin Tutek
Stephanie Brandl @stephaniebrandl.bsky.social · 10/02/2026
I am looking for 2 emergency reviewers for the ARR Ethics, Bias & Fairness track. Please DM me if you are available 🙏
066