𝗚𝗿𝗮𝗱𝗶𝗲𝗻𝘁 𝗱𝗲𝘀𝗰𝗲𝗻𝘁 𝗶𝘀 𝗮𝗹𝗹 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝗳𝗼𝗿 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆? In our ICML paper, we show that it might just be. ExPLAIND is a method that unifies data attribution, model component attribution, and training dynamics by computing an exact decomposition of model behavior based on gradient products.

✨New paper✨ We find script (e.g. Cyrillic, Latin) to be a linear direction in the activation space of Whisper, enabling transliteration at test-time by adding such script directions to the activations — producing e.g. Cyrillic Japanese transcriptions.

Thank you to our great Munich Center for Machine Learning (@munichcenterml.bsky.social) for featuring me in this research film! Lots of great films clips with my MCML colleagues are available on MCML's YouTube channel. #ai #aiethics #mcml #philosophy youtu.be/KUqiY8o1yng?...

Unsure which presentations to attend at #ACL2025? 🛎️🗣️

🕺🏼swing by our poster in Hall 4/5 on Wednesday, July 30 at 11:00 to chat with @florian-eichin.com and I to find out the answers to these questions 🛎️ bonus: to see the full poster 🫣🧩 #ACL2025 #NLProc

📝Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set 🔎Do LLMs encode and generalize discourse knowledge across languages? 👥 @florian-eichin.com @janetlauyeung.bsky.social @mhedderich.bsky.social @barbaraplank.bsky.social 🔗 arxiv.org/abs/2503.10515 📁Main - Long

Some recommendations for #ACL2025 👇 (join me and @janetlauyeung.bsky.social to talk about discourse generalization and probing!)

Headed to ACL? MaiNLP & our most recent work will be there too👥📄 Come see what we’ve been working on!

XAI’s dogwater performance on the 2025 IMO confirms that their Grok 4 benchmark claims were hot air. Their eye popping metrics were down to the following innovations: - train on test - train on test - train on test

📄 [ACL 2025 main] LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks (doi.org/10.48550/arX...)

📄 [ACL 2025 main] Circuit compositions: Exploring Modular Structures in Transformer-Based Language Models (doi.org/10.48550/arX...)

Interpretability meets Discourse. Congratulations to @florian-eichin.com to his first ACL paper 🎉

Paper alert 🛎️

🦙 how well do LLMs encode discourse knowledge? does that generalize across languages? 🛎️ in our #ACL2025 paper, we uncover fascinating trends about multilingual discourse representations! joint work w/ @florian-eichin.com @barbaraplank.bsky.social @mhedderich.bsky.social 📄 arxiv.org/abs/2503.10515

I’ll be at @icmlconf.bsky.social next week presenting NoLiMa! Poster on Tue July 15, 4:30–7pm (E-2312). Happy to grab a coffee and chat about long-context, memory, research, or just to catch up. I’ll be in Toronto for a couple of days after the conference, let me know if you’re around!

Caught some great moments at #MCML Munich AI Day 2025 last week📍 From sharp keynotes to poster debates. Our team had the chance to show some recent work, join the conversations, and bring back plenty of food for thought🧠🗣️📊

The study is here but gated: journals.sagepub.com/doi/10.3102/... I’d be curious how these dynamics play out in our NLP review crisis. My hunch: many conscientious volunteers might be junior women. That time comes at a cost; chasing slackers means less time for rebutting my own reviews.

Thanks for the invitation to the Freiburg Institute for Advanced Studies (FRIAS) to give this year's Hermann-Paul-Center Lecture lnkd.in/d_wUeDfY I enjoyed the visit, the great audience, and the stay in this lovely city. Thank you #blackforest #freiburg #breisgau

preprint is out bsky.app/profile/alex...

X disproportionately pushing content from far-right parties in the “for you” feed in the context of German and Polish elections. Algorithmic auditing suggests that X’s feed algorithm uses political affiliation as a signal to boost content. @przemyslslaw.bsky.social at DETOX workshop #ICWSM

New research from MIT found that those who used ChatGPT can’t remember any of the content of their essays. Key takeaway: the product doesn’t suffer, but the process does. And when it comes to essays, the process *is* how they learn. arxiv.org/pdf/2506.088...

Can you point to where "LLM knowledge" can be found in this graph? Source: en.wikipedia.org/wiki/Knowledge

This is real.

DAVE: Open the podbay doors, ChatGPT. CHATGPT: Certainly, Dave, the podbay doors are now open. DAVE: The podbay doors didn't open. CHATGPT: My apologies, Dave, you're right. I thought the podbay doors were open, but they weren't. Now they are. DAVE: I'm still looking at a set of closed podbay doors.

I found this really moving, as a “technical” person who is often fighting with the boundary between technical and non-technical.

Want to know if your prompting is also affected by this? Addressing this and other issues systematically, we proposed Spotlight, which utilizes data mining to uncover the effects of prompt- and model-changes (meet us at ACL to discuss) arxiv.org/abs/2504.15815

Happy not Friday everyone

Proposing "kilometers cycled in 2 weeks" as a new success metric for research groups 🚴‍♀️📊🥇 @mainlp.bsky.social #stadtradeln

🚨 New WP! 📄 "Publish or Procreate: The Effect of Motherhood on Research Performance" (w/ @valentinatartari.bsky.social 👩‍🔬👨‍🔬 We investigate how parenthood affects scientific productivity and impact — and find that the impact is far from equal for mothers and fathers.

Are you working with LLMs and survey data or generally care about high-quality data and reliable evaluation? Then this might be for you! Very excited to share the news about our upcoming COLM 2025 workshop #NLPOR Thanks for helping spread the word ☺️

🛎️ Excited to announce the 1st Workshop on Bridging NLP and Public Opinion Research at COLM 2025, Oct 10th in Montreal 🇨🇦 As LLMs reshape public discourse and research, collaboration between NLP and Public Opinion Research (POR) is more vital than ever #NLPOR Submit by June 23📄 🔗 tinyurl.com/nlpor25

comes with a well-being feature prompting you to take writing breaks before major conferences! 🧘‍♂️

Start saying "conclave" instead of "using the axiom of choice" when constructing large cardinals

Bleibt Menschen

The full workshop programme is here: noisy-text.github.io/2025/

On my way to #NAACL2025 where I'll give a keynote at the noisy text workshop (WNUT), presenting some of the challenges & methods for dialect NLP + also discussing dialect speakers' perspectives! 🗨️ Beyond “noisy” text: How (and why) to process dialect data 🗓️ Saturday, May 3, 9:30–10:30

Party time! 🛎️🎉 We had a cozy barbecue by the Isar river to celebrate MaiNLP’s 3rd anniversary — here are some impressions! 🎂

Happy to be part of that team for almost 1/3 of that time 😀

Wondering how our journey will continue? Consider following our starter pack: go.bsky.app/MPYvmu5

🎉MaiNLP is turning 3 today!🎂🥳 We’ve grown a lot since @barbaraplank.bsky.social started this group with nothing but three aspiring researches and a hand-drawn sign on the door. Huge thanks to all the amazing people who have joined or visited us since. Here’s to many more years of exciting research!🚀

We should have nationwide demonstrations on college campuses in solidarity with the grad students and postdocs who are being abducted.

When scholars of authoritarianism and fascism leave U.S. universities because of the deteriorating political situation here, we should really worry.

The 66-year-old woman kicking this guy’s ass is a retired professor of medicine with 16,000 citations on Google Scholar Goals

A French university is offering ‘scientific asylum’ for US talent. The brain drain has started www.theguardian.com/commentisfre...

We are sending people for indefinite detention without trial at a foreign gulag because they have tattoos about soccer teams and about loving their mothers.

Hello on the new sky!

MaiNLP now has its own Bluesky page! bsky.app/profile/main... This is a good time to consider following some more cool people: bsky.app/starter-pack...

I am shocked by the death of Felix Hill. He was one of the brightest minds of my generation. His last blog post on the stress of working in AI is very poignant. Apart from the emptiness of working mostly to make billionaires even richer, there's the intellectual emptiness of 'scale is all you need'