Programme

09:00	Welcome and Introduction (organisers)
09:10	Invited Keynote - Yufang Hou Synthesizing Scientific Knowledge: From Biomedical Evidence to NLP Claims
09:50 10:10	Session 1: SHARED TASK OVERVIEW PAPERS ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims Raia Abu Ahmad, Max Upravitelev, Aida Usmanova, Veronika Solopova and Georg Rehm The Software Mention Detection and Coreference Resolution Shared Task 2026 Sharmila Upadhyaya, Wolfgang Otto, Julia Matela, Frank Krüger and Stefan Dietze
10:30	Coffee Break & Poster Session
11:00 11:20 11:40 12:00 12:20 12:40 12:50	Session 2: SCHOLARLY INFRASTRUCTURE AND DATA FOUNDATIONS Track A: Knowledge Graphs & Taxonomy Comparing LLM-Based Knowledge Graph Extraction Approaches on Literary Studies in Spanish: A Case Study on Orbis Tertius Federico Cortes Enhancing Scholarly Knowledge Graphs via Domain-Specific Entity Detection and Linking Nicolau Duran-Silva, César A. Parra-Rojas, Pablo Accuosto, Julian Moreno-Schneider and Georg Rehm UniCite: A Dataset and Unified Hierarchical Taxonomy for Multi-Dimensional Citation Analysis Amina Mourky, Elena Leitner, Julian Moreno-Schneider, Raia Abu Ahmad, Ekaterina Borisova and Georg Rehm Track B: Domain-Specific Resources & Metadata Beyond Abstracts: A Biomedical MeSH Indexing Corpus Incorporating Summarized Methods Sections Sujoy Datta, Robert E. Mercer and Xindi Wang AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics Atilla Kaan Alkan, Felix Grezes, Sergi Blanco-Cuaresma, Jennifer Lynn Bartlett, Daniel Chivvis, Anna Kelbert, Kelly Lockhart and Alberto Accomazzi Normalizing section names and structure of scientific articles Nicolau Duran-Silva, Julian Moreno-Schneider, César A. Parra-Rojas and Georg Rehm Generating Research Data Metadata from Their Accompanying README Files Kotaro Sekido, Yu Watanabe, Koichiro Ito and Shigeki Matsubara
13:00	Lunch Break
14:00 14:20 14:40 15:00 15:20 15:40	Session 3: RELIABILITY, REACH & SCALE Track C: Factuality & Agentic Reasoning Enhancing Factuality and Transparency in Generative Models for Biomedical Question Answering Ankita Behura, Siting Liang and Daniel Sonntag The Linguist's Lie Detector: Benchmarking Linguistic Veracity in Large Language Models Lucía Catalán Gris, Kim Gerdes and John S. Y. Lee Improving Completeness in Deep Research Agents through Targeted Enrichment Jesse Wonnink, Jakub Zavrel and Paul Groth Track D: Multilingualism & Model Optimization Transferring Scientific English Pre-Trained Language Models to Multiple Languages Using Cross-Lingual Transfer Nikolas Ching-Pu Rauscher, Fabio Barth and Georg Rehm Evaluating Generative Large Language Models for Portuguese Scientific Information Extraction Tomás Pinto, Catarina Silva and Hugo Goncalo Oliveira Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models Florian Kelber, Matthias Jobst, Yuni Susanti and Michael Färber
16:00	Coffee Break & Poster Session
16:30	Invited Keynote - Iryna Gurevych Welcoming AI as a New Colleague: How Should We Evaluate AI for Science?
17:15	Wrap-up and end of workshop