Matthias Hagen

.- Conference Papers..- Do Physiological Signals Improve Both Generalization and Personal Perception of Sexism in Memes?..- Model Comparison for Kazakh Semantic Reuse Detection Across Pairwise, News, and Long-Document Evaluation..- Generative AI-based Uncertainty-aware IR Evaluation with Distributional Evaluation..- KangarooBench: A Native German Benchmark for Evaluating the Modality Gap in Visual Mathematics..- Privacy-Preserving NLP for a Low-Resource Language: Benchmarking LLM-Based Personally Identifiable Information Anonymization in Slovene..- Named Entity Masking for De-Biasing Text Classification: Experiments with German Datasets..- Contrastive Learning for Authorship Verification..- Scope Matters: A Hallucination-Aware Evaluation of Retrieval Strategies for Multilingual RAG..- A Controlled Study of Evidence Quality in LLM-Based Numerical Claim Verification..- A corpus for evaluating neutrality in political biographies on Wikipedia: NeutralWikiPol-fr..- Are Lexical Bindings Important for SPLADE?..- Evaluating Pre-Training Objectives for TITE..- Query Understanding with Large Language Models..- Category-Conditioned Persona Retrieval for Multi-Session Dialogue: A Method and a Gold-Annotation-Compatible Retrieval Metric..- Best of CLEF 2025 Labs..- Trusting Gut Instincts: A Fine-Grained Error Analysis of Transformer-Based Structured Data Extraction from...