Konvens 2026
Main venue:
- Langchen Huang, Sebastian Padó, and Franziska Weeber. Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing. Proceedings of KONVENS. Hamburg, Germany, 2026.
- Sven Naber, Marina Aziz, Diego Frassinelli, and Sabine Schulte im Walde. KNN-ConcrItUp! A Language-Agnostic, Interactive, and Interpretable System for Extrapolating Concreteness Norms. Proceedings of KONVENS. Hamburg, Germany, 2026.
- Nina Vikhrova, Johannes Kühling, Sebastian Haunss, and Sebastian Padó. Comparing and Modeling Argumentation in German Political Communication across Arenas. Proceedings of KONVENS. Hamburg, Germany, 2026.
Associated workshops:
- Anna Golub and Sebastian Padó. Comparing Architectures for Supervised Political Scaling. Proceedings of the 6th Workshop on Computational Linguistics for the Political and Social Sciences (CPSS) at KONVENS. Hamburg, Germany, 2026.
- Ksenia Merzlyakova, Sebastian Padó, and Franziska Weeber. Effect of Answer Format Variation on Gender Bias in Large Language Models. Proceedings of the 6th Workshop on Computational Linguistics for the Political and Social Sciences (CPSS) at KONVENS. Hamburg, Germany, 2026.
EMNLP 2026
Main venue:
- Sinan Kurtyigit, Sabine Schulte im Walde, and Alexander Fraser. Learning the Cue or Learning the Word? Analyzing Generalization in Metaphor Detection for Verbs. Proceedings of EMNLP. Budapest, Hungary, 2026.
- Titus von der Malsburg and Sebastian Padó. Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects. Proceedings of EMNLP. Budapest, Hungary, 2026.
- Hongyu Chen, Neele Falk, Michael Roth, and Agnieszka Falenska. Contrast Comes at a Cost: Prompting Large Language Models for Perception-Centered Gender Style Trasfer. Proceedings of EMNLP. Budapest, Hungary, 2026.
Associated workshops:
- Abdul Razaq Vahidi and Sebastian Padó. When Cross-Lingual Consistency Is Not Enough: Diagnostics for Low-Resource Political Actor Portrayal. Proceedings of the 6th Multilingual Representation Learning Workshop. Budapest, Hungary, 2026.
- Nikta Yekrang Safakar and Sebastian Padó. Testing Language Model Sensitivity to Object-Anaphoric Accessibility: Persian ye(k) and English indefinite this. Proceedings of the 6th Multilingual Representation Learning Workshop. Budapest, Hungary, 2026.
- David Tsoi and Esra Dönmez. Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment. Proceedings of the First Workshop on Pluralistic AI & NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA). Budapest, Hungary, 2026.
- Gayane Ghazaryan and Esra Dönmez. Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks. Proceedings of the First Workshop on Pluralistic AI & NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA). Budapest, Hungary, 2026.
- Elisa Bassignana*, Lorena Calvo-Bartolomé*, Esra Dönmez*, Marlene Lutz*, Arianna Muti*, Vera Neplenbroek*, and Donya Rooein*. SEAL: SocioEconomic Alignment in LLMs. Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI). Budapest, Hungary, 2026.