Publications

Extending Information Bottleneck Attribution to Video Sequences for Deepfake Detection
Veronika Solopova, Lucas Schmidt, Dr. Vera Schmitt, Dorothea Kolossa
PDF Cite
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, Michael a Hedderich, Sebastian Lapuschkin, Wojciech Samek, Dr. Vera Schmitt
PDF Cite
Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II
Dr. Vera Schmitt, Niklas Kruse, Premtim Sahitaj, Julius Schöning
PDF Cite
Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation
Lynn Janzen, Üveys Eroglu, Dorothea Kolossa, Pia Knöferle, Sebastian Möller, Dr. Vera Schmitt, Veronika Solopova
PDF Cite
Retrieving Climate Change Disinformation by Narrative
Max Upravitelev, Veronika Solopova, Charlott Jakob, Premtim Sahitaj, Dr. Vera Schmitt
PDF Cite
Multiperspectivity as a Resource for Narrative Similarity Prediction
Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob, Premtim Sahitaj, Ariana Sahitaj, Dr. Vera Schmitt
PDF Cite
Take It All: Ensemble Retrieval for Multimodal Evidence Aggregation
Max Upravitelev, Veronika Solopova, Premtim Sahitaj, Ariana Sahitaj, Charlott Jakob, Sebastian Möller, Dr. Vera Schmitt
PDF Cite
Selective Multimodal Retrieval for Automated Verification of Image–Text Claims
Yoana Tsoneva, Paul-Conrad Feig, Jiaao Li, Veronika Solopova, Neda Foroutan, Arthur Hilbert, Dr. Vera Schmitt
PDF Cite
News Credibility Assessment by LLMs and Humans: Implications for Political Bias
Pia Wenzel Neves, Charlott Jakob, Dr. Vera Schmitt
PDF Cite
Persona Prompting as a Lens on LLM Social Reasoning
Jing Yang, Moritz Hechtbauer, Elisabeth Khalilov, Evelyn Luise Brinkmann, Dr. Vera Schmitt, Dr. Nils Feldhus
PDF Cite
Order in the Evaluation Court: A Critical Analysis of NLG Evaluation Trends
Jing Yang, Dr. Nils Feldhus, Salar Mohtaj, Leonhard Hennig, Qianli Wang, Eleni Metheniti, Sherzod Hakimov, Charlott Jakob, Veronika Solopova, Konrad Rieck, David Schlangen, Sebastian Möller, Dr. Vera Schmitt
PDF Cite
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt, Dr. Nils Feldhus, Christin Seifert, Hinrich Schütze, Sebastian Möller, Dr. Vera Schmitt
PDF Cite
Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
Qianli Wang, Dr. Nils Feldhus, Pepa Atanasova, Fedor Splitt, Simon Ostermann, Sebastian Möller, Dr. Vera Schmitt
PDF Cite
AI Development and Governance: Navigating Trust, Transparency, Innovation, and the Challenges of Information Warfare
Dr. Vera Schmitt
PDF
Deepfakes–Unsere neue Realität?
Dr. Vera Schmitt
PDF Cite
Truth or twist? optimal model selection for reliable label flipping evaluation in llm-based counterfactuals
Qianli Wang, Dr. Nils Feldhus, Luis-Felipe Villa-Arenas, Christin Seifert, Sebastian Möller, Dr. Vera Schmitt
PDF Cite
PolBiX: Detecting LLMs Political Bias in Fact-Checking through X-phemisms
Charlott Jakob, David Harbecke, Patrick Parschan, Pia Wenzel Neves, Vera Schmitt
PDF Cite
Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems
Qianli Wang, Tatiana Anikina, Dr. Nils Feldhus, Simon Ostermann, Fedor Splitt, Jiaao Li, Yoana Tsoneva, Sebastian Möller, Vera Schmitt
PDF Cite
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
Qianli Wang, Dr. Nils Feldhus, Simon Ostermann, Luis-Felipe Villa-Arenas, Prof. Sebastian Möller, Dr. Vera Schmitt
PDF Cite
Exploring Semantic Filtering Heuristics For Efficient Claim Verification
Max Upravitelev, Premtim Sahitaj, Arthur Hilbert, Veronika Solopova, Jing Yang, Dr. Nils Feldhus, Tatiana Anikina, Simon Ostermann, Vera Schmitt
PDF
Improving Sentiment Analysis for Ukrainian Social Media Code-Switching Data
Yurii Shynkarov, Veronika Solopova, Vera Schmitt
PDF
Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence
Ariana Sahitaj, Premtim Sahitaj, Veronika Solopova, Jiaao Li, Sebastian Möller, Vera Schmitt
PDF
Comparing LLMs and BERT-based Classifiers for Resource-Sensitive Claim Verification in Social Media
Max Upravitelev, Nicolau Duran-Silva, Christian Woerle, Giuseppe Guarino, Salar Mohtaj, Jing Yang, Veronika Solopova, Vera Schmitt
PDF
MAD25 - 4th ACM International Workshop on Multimedia AI against Disinformation
Dan-Cristian Stanciu, Bogdan Ionescu, Symeon Papadopoulos, Giorgos Kordopatis-Zilos, Adrian Popescu, Roberto Caldelli, Milica Gerhardt, Vera Schmitt
PDF
Integrating Video, Text, and Images for Multimodal Disinformation Detection
Thomas Hetzner, Veronika Solopova, Vera Schmitt, Dorothea Kolossa
PDF
Beyond Transparency: Evaluating Explainability in AI-Supported Fact-Checking
Vera Schmitt, Isabel Bezzaoui, Charlott Jakob, Premtim Sahitaj, Qianli Wang, Arthur Hilbert, Max Upravitelev, Jonas Fegert, Sebastian Möller, Veronika Solopova
PDF
Utilising Large Language Models for Adversarial Attacks in Text-to-SQL: A Perpetrator and Victim Approach
Ariana Sahitaj, Markus Nilles, Ralf Schenkel, Dr. Vera Schmitt
PDF Cite
Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs
Premtim Sahitaj, Iffat Maab, Junichi Yamagishi, Jawan Kolanowski, Prof. Sebastian Möller, Dr. Vera Schmitt
PDF Cite
ITG Position Paper: Large Language Models are Transformers in Artificial Intelligence, Industry, Education, and Society
Prof. Rainer Martin, Prof. Stefan Brüggenwirth, Dr. Aljoscha Burchard, Prof. Tim Fingscheidt, Prof. Holger Hoos, Prof. Klaus Illgner, Dr. Henrik Junklewitz, Prof. André Kaup, Dr. Katharina Von Knop, Dr. Joachim Köhler, Prof. Gitta Kutyniok, Prof. Dorothea Kolossa, Prof. Sebastian Möller, Dr. Ralf Schlüter, Dr. David Thulke, Dr. Vera Schmitt, Prof. Ingo Siegert, Dr. Volker Ziegler
PDF
Anchored Alignment for Self-Explanations Enhancement
Luis-Felipe Villa-Arenas, Ata Nizamoglu, Qianli Wang, Prof. Sebastian Möller, Dr. Vera Schmitt
PDF Cite
From Construction to Application: Advancing Argument Mining with the Large-Scale KIALOPRIME Dataset
Premtim Sahitaj, Ramon Ruiz-Dolz, Ariana Sahitaj, Ata Nizamoglu, Dr. Vera Schmitt, Salar Mohtaj, Prof. Sebastian Möller
PDF
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
Qianli Wang, Tatiana Anikina, Dr. Nils Feldhus, Simon Ostermann, Prof. Sebastian Möller, Dr. Vera Schmitt
PDF Cite
CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems
Qianli Wang, Tatiana Anikina, Dr. Nils Feldhus, Dr. Simon Ostermann, Prof. Sebastian Möller
PDF Cite
Disentangling User States in QoE: Situation-Dependent and Independent Factors
Robert P Spang, Maximilian Warsinke, Dr. Vera Schmitt, Luis-Felipe Villa-Arenas, Navid Ashrafi, Prof. Sebastian Möller
PDF Cite
NewsPolyML: Multi-lingual European News Fake Assessment Dataset
Salar Mohtaj, Ata Nizamoglu, Premtim Sahitaj, Charlott Jakob, Dr. Vera Schmitt, Prof. Sebastian Möller
PDF Cite
Implications of Regulations on Large Generative AI Models in the Super-Election Year and the Impact on Disinformation
Dr. Vera Schmitt, Jakob Tesch, Eva Lopez, Luis-Felipe Villa-Areas, Tim Polzehl, Aljoscha Burchardt, Konstanze Neumann, Salar Mohtaj, Prof. Sebastian Möller
PDF Cite
Evaluating Human-Centered AI Explanations: Introduction of an XAI Evaluation Framework for Fact-Checking
Dr. Vera Schmitt, Balázs Patrik Csomor, Joachim Meyer, Luis-Felipe Villa-Areas, Charlott Jakob, Tim Polzehl, Prof. Sebastian Möller
PDF Cite
The Role of Explainability in Collaborative Human-AI Disinformation Detection
Dr. Vera Schmitt, Luis-Felipe Villa-Arenas, Dr. Nils Feldhus, Joachim Meyer, Robert P Spang, Prof. Sebastian Möller
PDF Cite
How Much is Your Instagram Data Worth? Economic Perspective of Privacy
Dr. Vera Schmitt, Paul Michel Dit Ferrer, Arooj Anwar Khan
PDF Cite
Classifying Sustainability Reports Using Companies Self-Assessments
Charlott Jakob, Dr. Vera Schmitt, Salar Mohtaj, Prof. Sebastian Möller
Cite Springer
Towards a Computational Framework for Distinguishing Critical and Conspiratorial Texts by Elaborating on the Context and Argumentation with LLMs
Ariana Sahitaj, Premtim Sahitaj, Salar Mohtaj, Prof. Sebastian Möller, Dr. Vera Schmitt
PDF
Privacy-Aware Decision Making: The Effect of Privacy Nudges on Privacy Awareness and the Monetary Assessment of Personal Information.
Dr. Vera Schmitt, James Nicholson, Prof. Sebastian Möller
PDF Cite
Augmented Political Leaning Detection: Leveraging Parliamentary Speeches for Classifying News Articles
Charlott Jakob, Pia Wenzel, Salar Mohtaj, Dr. Vera Schmitt
PDF Cite
What is Your Information Worth? A Systematic Analysis of the Endowment Effect of Different Data Types
Daniel Sivizaca Conde, Premtim Sahitaj, Dr. Vera Schmitt, Prof. Sebastian Möller
PDF Cite
How Risky is Multimodal Fake News Detection? A Review of Cross-Modal Learning Approaches under EU AI Act Constrains
Razieh Khamsehashari, Dr. Vera Schmitt, Tim Polzehl, Salar Mohtaj, Prof. Sebastian Möller
PDF Cite
A Transfer Learning Approach for SDGs Classification of Sustainability Reports
Ata Nizamoglu, Lea Dahm, Talia Sari, Dr. Vera Schmitt, Salar Mohtaj, Prof. Sebastian Möller
PDF Cite
Unraveling the Hangry Rater: Non-linear Effects of Hunger on Multimedia Quality Perception
Robert P Spang, Wafaa Wardah, Dr. Vera Schmitt, Prof. Sebastian Möller
PDF Cite
Comparing Simulated and Real Conversations for QoE Assessments: Insights from ARKit-Based Facial Configuration Analyses
Robert P. Spang,, Wafaa Wardah, Dr. Vera Schmitt, Prof. Sebastian Möller
PDF Cite
Fighting Disinformation: Overview of Recent AI-Based Collaborative Human-Computer Interaction for Intelligent Decision Support Systems
Prof. Sebastian Möller, Tim Polzehl, Dr. Vera Schmitt, Dr. Nils Feldhus, Joachim Meyer
PDF Cite
Multi-Task Learning for German Text Readability
Salar Mohtaj, Dr. Vera Schmitt, Razieh Khamsehashari, Prof. Sebastian Möller
PDF Cite
A Feature Extraction based Model for Hate Speech Identification
Salar Mohtaj, Dr. Vera Schmitt, Prof. Sebastian Möller
PDF Cite
Towards Automatic Green Claim Detection
Vinicius Woloszyn, Joseph Kobti, Dr. Vera Schmitt
PDF Cite
Implications of the New Regulation Proposed by the European Commission on Automatic Content Moderation
Dr. Vera Schmitt, Dr. Veronika Solopova, Vinicius Woloszyn, Jessica J. De Pino Pinhal
PDF Cite
Towards a Novel Benchmark for Automatic Generation of ClaimReview Markup
Vinicius Woloszyn, Eduardo G. Cortes, Rafael Amantea, Dr. Vera Schmitt, Dante A. C. Barone, Prof. Sebastian Möller
PDF Cite