GroNLP

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

[Jirui Qi @Jirui_Qi]

[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: https://t.co/SwCR6CYpdA

[Jirui Qi @Jirui_Qi]

✨ 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: https://t.co/qgQkZ69tog
(w/ @AriannaBisazza @raquel_dmg)

#NLProc

[Yevgen Matusevych @Yevgen_M]

Last week to apply for our PhD position!

[Arianna Bisazza #EMNLP 🇨🇳 @AriannaBisazza]

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)

[Yevgen Matusevych @Yevgen_M]

Apply for our PhD position in language acquisition / computational linguistics in Groningen until 24 April! Job ad is here:
https://t.co/0AAIU6Cy3o

[Arianna Bisazza #EMNLP 🇨🇳 @AriannaBisazza]

📣 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.

[Arianna Bisazza #EMNLP 🇨🇳 @AriannaBisazza]

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

[GroNLP @GroNlp]

The GOLEM Knowledge Graph: Modelling Fiction and Narrative Across Domains

GroNLP's Dr. Franziska Pannach is presenting the #GOLEM Ontology and Knowledge Graph at the International Conference Linked Open Data and Literary Studies in Berlin #LODaLS #DH #CLS

[GroNLP @GroNlp]

🌴We had a great time at #EMNLP2024 presenting our works, meeting old friends, getting to know new people, and winning some prizes (Best Social Impact Award at #EMNLP2024 Main and @babyLMchallenge award #CoNLL2024) 🤩

[Tommaso Caselli @tommasoc80.bsky.social @tommaso_caselli]

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

[Gabriele Sarti @gsarti_]

If you're attending #EMNLP2024 don't miss our latest works in interpretability and generation 👇

[GroNLP @GroNlp]

Federico Pianzola (and colleagues): "Analysing the Reception of Fiction Novels Across Languages"

Franziska Pannach (together with @TWdiBruno): "Digital Methods for Mythological Research"

[GroNLP @GroNlp]

We are proud to announce that not one, but two of our colleagues are (co-)hosting workshops at the Computational Humanities Research Conference in Aarhus this year!

https://t.co/yqhmMV9OKJ

#digitalhumanities #CHR2024 #narrative #fiction #dm4myth

[GroNLP @GroNlp]

#EMNLP2024
Language Is Scary When Overanalyzed: Unpacking Implied Misogynistic Reasoning with Argumentation Theory-Driven Prompts.
@Aramona4 , Federico Ruggeri, @khalid_ikh, @tommaso_caselli

📜https://t.co/c1sIewqEyi

[GroNLP @GroNlp]

Check out our group’s most recent works at #EMNLP2024, #CoNLL2024 and Computational Linguistics!
Big congrats to all the authors and collaborators! 🥳

[GroNLP @GroNlp]

#EMNLP2024
Scope-enhanced Compositional Semantic Parsing for DRT
Xiulin Yang, Jonas Groschwitz, Alexander Koller & Johan Bos

📜https://t.co/UT3zErv5R1

[GroNLP @GroNlp]

Computational Linguistics Journal
Neural Semantic Parsing with Extremely Rich Symbolic Meaning Representations
@XiaoZhang2469 @gosseb Johan Bos
📜https://t.co/vnkmyJFj7k

[GroNLP @GroNlp]

#EMNLP2024 Findings
Improving Argument Effectiveness Across Ideologies using Instruction-tuned Large Language Models
Roxanne El Baff, @khalid_ikh, Milad Alshomary, Kai Konen, Benno Stein, and Henning Wachsmuth

📜https://t.co/JI6NwtqXC4