We are pleased to share that 10 papers authored or co-authored by UKP members have been accepted for the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) in Suzhou. Congratulations to everyone involved!

The 8 main conference papers are:

»Towards Automated Error Discovery: A Study in Conversational AI« by Dominic Petrak, Thy Thy Tran, Iryna Gurevych

»MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors« by Jakub Macina, Nico Daheim, Ido Hakimi, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan

»Preemptive Detection and Correction of Misaligned Actions in LLM Agents« by Haishuo Fang, Xiaodan Zhu, Iryna Gurevych

»From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning« by David Dinucu-Jianu, Jakub Macina, Nico Daheim, Ido Hakimi, Iryna Gurevych, Mrinmaya Sachan

»From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs« by Muhammad Farid Adilazuarda, Chen Cecilia Liu, Iryna Gurevych, Alham Fikri Aji

»The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors« by Abdelrahman Sadallah, Tim Baumgärtner, Iryna Gurevych, Ted Briscoe

»$\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection« by Daniil Orel, Indraneil Paul, Iryna Gurevych, Preslav Nakov

»Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions« by Rachneet Singh Sachdeva, Rima Hazra, Iryna Gurevych

»Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers« by Tommaso Green, Martin Gubri, Haritz Puerto, Sangdoo Yun, Seong Joon Oh

The Findings paper is:

»Identifying Aspects in Peer Reviews« by Sheng Lu, Ilia Kuznetsov, Iryna Gurevych

Congratulations to all authors! We look forward to seeing you in Suzhou!