🦁📢We're hiring a PhD student to work on interpretability for Protein Language Models, and there are now two weeks left to apply! Find out more on our website: lionlabnlp.github.io/jobs/ai…

🦁LION Lab is hiring! 🧑‍🔬One fully funded PhD student (TVL-13 100%) for 3 years 🧪Topic: Interpretability for Protein Language Models 👥Advised by @LAWeissweiler together with Clara Schoeder 🌍Leipzig, Germany 🔗Apply by Oct 15 lionlabnlp.github.io/jobs/ai… Please share! #NLProc #NLP

We hope to see the UniDivers again soon in other settings😊 Fun fact: the old town of Bucharest has been called the Lipscani District since the 17th century, because most of the wares sold on the high street at the time originated from Leipzig!

It was great seeing everyone again at the last Unidive General Meeting in Bucharest! Jacob Lee Suchardt presented his EMNLP 2025 paper on the Transcription of Unseen Languages with Speech-to-IPA Models, and we celebrated the past four years of UniDive and all the friends we made

Yesterday we had @anja_reu from Technion visiting us to give a talk on Interpretability for Generative Information Retrieval. The talk was a cool example to show that interpretability can also be actionable. Thank you very much for joining us, Anja!

🗣️Today we had the pleasure of hosting Bastian Bunzeck for a talk on how LLMs are not usage-based (yet). We learned a lot about the challenges of training smaller language models on dialogue data and evaluating from a production-based perspective. Thanks for coming, Bastian!

We had a great time yesterday listening to @dmort27 explain how The Reconstruction Will Not Be Supervised — because the Comparative Method of reconstructing the pronunciation of earlier languages can be automated using agents! Thanks for visiting, David!

🗣️We were delighted yesterday to welcome Nina Böbel to our lab for a talk on Language as a Linguistic Network. Thanks for coming and patiently teaching us about construction networks, Nina!

🦁

🔗You can find more information about our work on our website: lionlabnlp.github.io

Toshiki Nakai has a B.A. in interdisciplinary studies from Waseda University🇯🇵 and an M.Sc. in Language Science and Technology from Saarland🇩🇪. He's interested in mechanistic interpretability for multilingual LLMs. Welcome, Toshiki!🥳

Jacob Lee Suchardt has a B.A. in Computational Linguistics and Japanese from Bochum🇩🇪 and an M.A. in Language Technology from Gothenburg🇸🇪. He's interested in multilinguality and linguistic competency of language models, as well as speech processing. Welcome, Jacob! 🥳

Hello world! We are LION(Linguistically-Oriented NLP) Lab, a new research group at Leipzig University, working on interpretability and evaluation of (multilingual) language models, and the application of NLP methods to linguistics, esp. typology! Meet our PhD students below🧵