23 papers
GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports
Veronika Solopova, Ivan Havlytskyi, Viktoria Skorik +1
Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their heterogeneity and…
From Repetition to Recognition: Inductive Discovery of Disinformation Narratives
Max Upravitelev, Veronika Solopova, Jing Yang +4
In disinformation datasets, narratives are often understood as recurring interpretive patterns that group texts under narrative labels. Recent work formalized narrative mining as i…
Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels
Yuliia Vistak, Viktoriia Makovska, Vera Schmitt +1
Detecting disinformation narratives on social media is challenging due to the scale of amplification, rapid evolution, and linguistic variability of online content. We propose a gr…
Uncovering Temporal Framing in the News
Tarek Mahmoud, Veronika Solopova, Premtim Sahitaj +7
Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpreta…
Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas
Lukas Stähelin, Veronika Solopova, Max Upravitelev +6
Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and…
From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence
Premtim Sahitaj, Jawan Kolanowski, Ariana Sahitaj +7
Fact-checking articles encode rich supporting evidence and reasoning, yet this evidence remains largely inaccessible to automated verification systems due to unstructured presentat…
Retrieving Climate Change Disinformation by Narrative
Max Upravitelev, Veronika Solopova, Charlott Jakob +3
Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives. Thus, we re-frame narrative detection as a retrieval…
ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims
Raia Abu Ahmad, Max Upravitelev, Aida Usmanova +2
Automatically verifying climate-related claims against scientific literature is a challenging task, complicated by the specialised nature of scholarly evidence and the diversity of…
Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation
Lynn Janzen, Üveys Eroglu, Dorothea Kolossa +4
LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programmin…
Multiperspectivity as a Resource for Narrative Similarity Prediction
Max Upravitelev, Veronika Solopova, Jing Yang +4
Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and t…
LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations
Veronika Solopova, Viktoria Skorik, Maksym Tereshchenko +2
Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researc…
Online Density-Based Clustering for Real-Time Narrative Evolution Monitorin
Ostap Vykhopen, Viktoria Skorik, Maksym Tereshchenko +1
Automated narrative intelligence systems for social media monitoring face significant scalability challenges when relying on batch clustering methods to process continuous data str…
What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025
Jing Yang, Nils Feldhus, Salar Mohtaj +10
As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) adoption has accelerated rapidly,…
Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR
Ostap Vykhopen, Viktoria Skorik, Maksym Tereshchenko +1
Large language models can already query databases, yet most existing systems remain reactive: they rely on explicit user prompts and do not actively explore data. We introduce DAR…
XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models
Ariana Sahitaj, Jiaao Li, Pia Wenzel Neves +5
This notebook reports the XplaiNLP submission to the CheckThat! 2025 shared task on multilingual subjectivity detection. We evaluate two approaches: (1) supervised fine-tuning of t…
Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence
Ariana Sahitaj, Premtim Sahitaj, Veronika Solopova +3
Propaganda detection on social media remains challenging due to task complexity and limited high-quality labeled data. This paper introduces a novel framework that combines human e…
MisinfoTeleGraph: Network-driven Misinformation Detection for German Telegram Messages
Lu Kalkbrenner, Veronika Solopova, Steffen Zeiler +2
Connectivity and message propagation are central, yet often underutilized, sources of information in misinformation detection -- especially on poorly moderated platforms such as Te…
From Trust to Truth: Actionable policies for the use of AI in fact-checking in Germany and Ukraine
Veronika Solopova
The rise of Artificial Intelligence (AI) presents unprecedented opportunities and challenges for journalism, fact-checking and media regulation. While AI offers tools to combat dis…
How desirable is alignment between LLMs and linguistically diverse human users?
Pia Knoeferle, Sebastian Möller, Dorothea Kolossa +2
We discuss how desirable it is that Large Language Models (LLMs) be able to adapt or align their language behavior with users who may be diverse in their language use. User diversi…
Extending Information Bottleneck Attribution to Video Sequences
Veronika Solopova, Lucas Schmidt, Dorothea Kolossa
We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explai…
Check News in One Click: NLP-Empowered Pro-Kremlin Propaganda Detection
Veronika Solopova, Viktoriia Herman, Christoph Benzmüller +1
Many European citizens become targets of the Kremlin propaganda campaigns, aiming to minimise public support for Ukraine, foster a climate of mistrust and disunity, and shape elect…
PapagAI:Automated Feedback for Reflective Essays
Veronika Solopova, Adrian Gruszczynski, Eiad Rostom +9
Written reflective practice is a regular exercise pre-service teachers perform during their higher education. Usually, their lecturers are expected to provide individual feedback,…
Automated multilingual detection of Pro-Kremlin propaganda in newspapers and Telegram posts
Veronika Solopova, Oana-Iuliana Popescu, Christoph Benzmüller +1
The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data reflecting opposing ideologies and narra…