🔍 Prof. Kementchedjhieva also discussed alternative approaches to improve vision-to-language alignment while maintaining strong language capabilities.
💬 We thank Prof. Kementchedjhieva for the insightful talk and the discussion with UKP members on multimodal modeling and the future of vision-language systems.
#UKPLab #MultimodalAI #VisionLanguageModels #NLP #GuestTalk #NLProc #MBZUAI #TUDa
Questions? Discussion? Reach out to us:
Andreas Waldis (UKP Lab/Technische Universität Darmstadt and HSLU Hochschule Luzern), Vagrant Gautam (Universität des Saarlandes), Anne Lauscher (Universität Hamburg), Dietrich Klakow (Universität des Saarlandes), and Iryna Gurevych (UKP Lab/Technische Universität Darmstadt)
#NLProc #Interpretability #LLMs #ExplainableAI #MechanisticInterpretability #AlignedProbing #ModelInternals
The 19th Conference of the European Chapter of the Association for Computational Linguistics (#EACL'26) is just around the corner.
Come join us in #Rabat or remotely this week!
https://2026.eacl.org/
LTG #Oslo has a strong presence, with four papers (co-)authored by the LTG members 🧵
📄 Paper: https://arxiv.org/abs/2508.07902
💻 Code and data: https://github.com/UKPLab/eacl2026-culturecare
🔗 Project: https://github.com/UKPLab/arxiv2025-culturecare
Follow the authors Chen Cecilia Liu, Hiba Arnaout, Nils Kovacic, and Iryna Gurevych from the UKP Lab, Technische Universität Darmstadt and hessian.ai, as well as Dana Atzil-Slonim from the Psychology Department, Bar-Ilan University.
See you this week in Rabat 🕌! #EACL2026
#UKPLab #CulturalNLP #ResponsibleAI #NLProc #NLP4MentalHealth #NLPsych #NLP #MentalHealth
Large language models (LLMs) show promise in offering emotional support and generating empathetic responses for individuals in distress, but their ability to deliver culturally sensitive support remains underexplored due to a lack of resources. In this work, we introduce CultureCare, the first dataset designed for this task, spanning four cultures and including 1729 distress messages, 1523 cultural signals, and 1041 support strategies with fine-grained emotional and cultural annotations. Leveraging CultureCare, we (i) develop and test four adaptation strategies for guiding three state-of-the-art LLMs toward culturally sensitive responses; (ii) conduct comprehensive evaluations using LLM-as-a-Judge, in-culture human annotators, and clinical psychologists; (iii) show that adapted LLMs outperform anonymous online peer responses, and that simple cultural role-play is insufficient for cultural sensitivity; and (iv) explore the application of LLMs in clinical training, where experts highlight their potential in fostering cultural competence in novice therapists.
See you at #EACL2026 in Rabat 🕌!
#LLMs #AI #NLP #NLProc #MachineUnlearning #AIPrivacy #AISafety #ExplainableAI #ResponsibleAI
Follow the authors: Serwar Basch (UKP Lab/hessian.AI/Technische Universität Darmstadt), Ilia Kuznetsov (UKP Lab/hessian.AI/Technische Universität Darmstadt), Tom Hope (The Hebrew University of Jerusalem/Ai2), and Iryna Gurevych (UKP Lab/hessian.AI/Technische Universität Darmstadt)
And say hi to us if you are also in Rabat! #EACL2026
#NLProc #UKPLab #NLP #LLMs #AI
#MultiDocumentReasoning #ZeroShotLearning #Evaluation #OpenScience #ComputerScience
Our take on de-anonymization with LLMs: It's all flawed. But doing it right might be actually impossible. Counter-opinions?
Read here https://arxiv.org/abs/2603.08207 (accepted to Computational Linguistics journal) and discuss with us at ACL
Follow the authors Osama Mohammed Afzal and Iryna Gurevych from the Ubiquitous Knowledge Processing (UKP) Lab, Technische Universität Darmstadt, as well as Preslav Nakov from MBZUAI (Mohamed bin Zayed University of Artificial Intelligence) and Tom Hope from Ai2.
See you this #EACL2026 in Rabat 🕌!
#UKPLab #NLP #NLProc #AI #PeerReview #AIforScience #ScientificPublishing #NoveltyDetection #Evaluation #OpenScience
👥 Justus-Jonas Erker (UKP Lab/Technische Universität Darmstadt), Nils Reimers (Cohere), Iryna Gurevych (UKP Lab/Technische Universität Darmstadt)
See you at Hashtag#EACL2026 in Rabat 🕌!
#UKPLab #NLP #NLProc #InformationRetrieval #DenseRetrieval #MultiHop #FactChecking #QuestionAnswering #RAG
New article on the evaluation of task-oriented chatbots: https://nejlt.ep.liu.se/article/view/5940
UKP Lab
LTG Oslo
Ivan Habernal
Emiel van Miltenburg