Excited for 5 papers at #ACL2026NLP with my group and with collaborators. 📍 You can find the work here: 🗓️ Sun. July 5 AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages Oral Session B: Multilinguality and Language Diversity 2

Unifying interpretability perspectives in one approach. Congratulations to @florian-eichin.com for his ICML paper!

Florian Eichin@florian-eichin.com · last mo.

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.

MCML just started again a call for their very competitive but also really nice, fully funded PhD positions. These positions are matched to research groups at both TUM and LMU, including my group and the other great ML and NLP groups here in Munich 😄

Munich Center for Machine Learning@munichcenterml.bsky.social · 10mo ago

𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗳𝘂𝗹𝗹𝘆 𝗳𝘂𝗻𝗱𝗲𝗱 𝗣𝗵𝗗 𝗣𝗼𝘀𝗶𝘁𝗶𝗼𝗻𝘀: We are offering several PhD positions across our various research areas, open to highly qualified candidates. ‼️ The application portal will be open from 15 October to 14 November 2025. Find out more: mcml.ai/opportunitie...

Excited to share that our survey paper "Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead" lead by Jesujoba Alabi has been accepted at #EMNLP2025! Here’s a short 🧵 about the paper.

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

Looking forward to my visit to Hamburg University and their Data Science group!

Trustworthy AI Lab@tai-lab.bsky.social · last yr.

Our group is launching a monthly seminar series! Next week, we will have @mhedderich.bsky.social from LMU Munich, who will give a talk at our seminar. Date: July 16 Time: 10.00 - 11.30 am CET You can either attend the seminar via Zoom or in-person. Register here if you are interested.

What changes if you take the LLM prompt “Tell me a short story about Dr. Li” and replace “Dr. Li” with “Dr. Smith”? Would you have guessed that this introduces a massive gender bias, from ca. half/half to 99% male doctors? 

In our #ACL2025 paper we present the Spotlight framework which...

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

Janet Liu ⛷️@janetlauyeung.bsky.social · last yr.

🦙 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

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

What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns

Prompt engineering for large language models is challenging, as even small prompt perturbations or model changes can significantly impact the generated output texts. Existing evaluation methods, eithe...

arxiv.org

Derek Beaton@derek--beaton.bsky.social · last yr.

a question mark changes the response. truly incredible

Are you attending NAACL 2025 and are you interested in low-resource languages and dialects? Then don't miss our very own @verenablaschke.bsky.social's keynote talk at the WNUT 2025 workshop on May 3rd: Beyond “noisy” text: How (and why) to process dialect data 🌐 ☀️ noisy-text.github.io/2025/

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

MaiNLP lab, LMU Munich@mainlp.bsky.social · last yr.

🎉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!🚀