@GroNlp

Natural Language Processing and Computational Linguistics group at the University of Groningen 🐮 [email protected]

 Groningen
rug.nl/research/clcg/research/cl/
Joined January 2020
  • Tweets375
  • Following269
  • Followers1.8K
48Media
[1/]💡New Paper Large reasoning models (LRMs) are strong in English — but how well do they reason in your language? Our latest work uncovers their limitation and a clear trade-off: Controlling Thinking Trace Language Comes at the Cost of Accuracy 📄Link: arxiv.org/abs/2505.22888
5
16
6
66
18,145
✨ New Paper ✨ [1/] Retrieving passages from many languages can boost retrieval augmented generation (RAG) performance, but how good are LLMs at dealing with multilingual contexts in the prompt? 📄 Check it out: arxiv.org/abs/2504.00597 (w/ @AriannaBisazza @raquel_dmg) #NLProc
1
3
1
11
1,323
Last week to apply for our PhD position!
Yevgen Matusevych@Yevgen_M26 Mar 2025
Apply for our PhD position in language acquisition / computational linguistics in Groningen until 24 April! Job ad is here: rug.nl/about-ug/work-with-us…
2
1
536
Modern LLMs "speak" hundreds of languages... but do they really? Multilinguality claims are often based on downstream tasks like QA & MT, while *formal* linguistic competence remains hard to gauge in lots of languages... Meet MultiBLiMP! (joint work w/@JumeletJ & @LAWeissweiler)
Jaap Jumelet@JumeletJ7 Apr 2025
✨New paper ✨ Introducing 🌍MultiBLiMP 1.0: A Massively Multilingual Benchmark of Minimal Pairs for Subject-Verb Agreement, covering 101 languages! We present over 125,000 minimal pairs and evaluate 17 LLMs, finding that support is still lacking for many languages. 🧵⬇️
1
2
18
1,024
Apply for our PhD position in language acquisition / computational linguistics in Groningen until 24 April! Job ad is here: rug.nl/about-ug/work-with-us…
Yevgen Matusevych@Yevgen_M7 Mar 2025
Interested in a paid PhD position in the Netherlands? Join me, Annemarie van Dooren, and @AriannaBisazza on a project to develop computational models of modal verb acquisition. A job ad will be out soon, but here's a preview: yevgen.web.rug.nl/phd.pdf
3
1
1
1,323
📣 Soon-to-open PhD position @GroNlp: Come work with Annemarie van Dooren, @Yevgen_M and myself on a new project bridging Computational Linguistics methods and Language Acquisition questions, with a focus on the learning of modal verbs.
Yevgen Matusevych@Yevgen_M7 Mar 2025
Interested in a paid PhD position in the Netherlands? Join me, Annemarie van Dooren, and @AriannaBisazza on a project to develop computational models of modal verb acquisition. A job ad will be out soon, but here's a preview: yevgen.web.rug.nl/phd.pdf
1
2
1
12
1,817
Fruit of a collaboration started just a few months ago, our investigation of how child-directed Variation Sets help learning in LMs has received a @babyLMchallenge award #CoNLL2024 #EMNLP2024 !! 🎉❤️ W/ amazing co-authors @_akari000 @Rodamille @akiyohukat_u and Yohei Oseki
Akari Haga@_akari00016 Nov 2024
👶I am happy to announce that our paper "BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency" received the ✨Outstanding Paper Award✨ at @babyLMchallenge !! #CoNLL2024 #EMNLP2024
1
4
43
4,440
Being at #EMNL2024 🌴? Come to visit our poster “Language is Scary when Over-Analyzed” (Jasmine 14:00-15:30) We frame misogyny detection as an Argumentative Reasoning task using LLMs. Curious about the results? Come and talk to us @Aramona4
9
1
29
3,335
If you're attending #EMNLP2024 don't miss our latest works in interpretability and generation 👇
1
3
27
1,429
Save the date for the 16th Advances in Quantitative Laryngology, Voice, and Speech Research (AQL) conference! 🌍 Groningen, the Netherlands ⏰ June 24 - 27th, 2025 📥 Abstract submission opens November 18th, 2024
1
8
22
1,253
Sustainability Week 2024: 'A more just and sustainable clothing sector is possible. What we need is a different narrative.' 🥻 Journalist and PhD student María Pilar Uribe Silva (@FacultyofArtsUG) tells us more about her ideas for the future of fashion👇 rug.nl/about-ug/latest-news/…
2
2
7
1,087
Check out the article @tejarebernik and I wrote on why kinematic speech measures are so important when studying those with motor speech disorders! Available in Dutch and English below ⬇️
University of Groningen@univgroningen8 Oct 2024
Praten doen we constant. Maar wist je dat er een complexe coördinatie van allerlei spieren voor nodig is? 👅 Onderzoek hiernaar kan volgens @ThomasTienkamp en @tejarebernik (@FacultyofArtsUG) helpen bij het verklaren en herstel van spraakstoornissen 🗣️ rug.nl/about-ug/latest-news/…
3
15
1,157
The #INCREC project has just published a new episode of the Visible Art of Translation podcast! In this episode I interview Natasha Press, a translator from Swedish, about her career of a literary translator and view on technology. Check it out! open.spotify.com/episode/2sh…

S1E9: Natasha Press "Creativity is the ability to get behind the text"

The Visible Art of Translation · Episode

open.spotify.com
1
7
376
Hoe kunnen verandering in spraak ons helpen om verschillende ziekten, evenals het proces van ouder worden, te begrijpen? 🗣️ Dat bestudeert @defneabur (@FacultyofArtsUG). Als nieuw lid voegt ze haar innovatieve onderzoek toe aan de @YAGroningen 👏👇 rug.nl/about-ug/latest-news/…
6
16
1,780
It was awesome to host the whole InDeep consortium in Groningen last week! @GroNlp @univgroningen Thanks a lot to invited speakers @Yevgen_M & Daniel Herrmann, and to all poster presenters!
Grzegorz Chrupała 🇪🇺🇺🇦@gchrupala24 Sep 2024
Indeep consortium meeting in Groningen, with @AriannaBisazza @wzuidema @gsarti_ @hmohebbi75 @JumeletJ @linguisticshen @antske @iris_hx and several others. projects.illc.uva.nl/indeep/
3
14
871
Model Internals-based RAG Evaluation (MIRAGE) 🌴 is accepted to #EMNLP2024 Main! ➡️ To celebrate, here's our new MIRAGE demo combining @InseqLib and Transformers-specific LRP: huggingface.co/spaces/gsarti…. Reach out if you want to catch up in Miami! 🤗🏖️

MIRAGE - a Hugging Face Space by gsarti

Model Internals to generate RAG citations

huggingface.co
Jirui Qi@Jirui_Qi21 Jun 2024
[1/8] Struggling with verifying the trustworthiness of RAG outputs? Check our latest work where we utilize *model internals* as a powerful and faithful tool for attributing answers to retrieved docs! (w/ @gsarti_ @AriannaBisazza @raquel_dmg) 📄: arxiv.org/abs/2406.13663 #NLProc
5
58
3,283
😀Paper accepted by Computational Linguistics journal! 🧑‍💻With @MeaningBank @gosseb, we built a WordNet-based taxonomical representation that shows better generalization. This could be a step for combining data-driven models with symbolic knowledge! arxiv.org/abs/2404.12698
2
2
17
654
Why do human languages look the way they do? Which learning constraints, communication pressures &group dynamics cause the emergence of common language properties? We introduce NeLLComX, a framework to study this w/ neural-net agents arxiv.org/abs/2407.13999 w/Y.Lian @VerhoefTessa
3
12
2
49
4,321
Excited to be at #CogSci2024! Here to present work on the emergence of common language properties using neural-net simulations (👀 our poster on dep.length minimization w/@Yuqing199704 @VerhoefTessa today 13.00) Generally interested in lang.acquisition/learnability & neural nets!
2
14
762
🎓 We're thrilled to host Gabriele Sarti (@gsarti_) in our PhD seminar series tomorrow, July 16th, from 12:00-13:00 in Oe67 BU 101! Join us for his talk on interpreting context usage in generative language models, featuring the Inseq toolkit and PECoRe framework. 🕛Don't miss it!
1
5
1
36
4,842
Load more