13 citations · 68 across the 49 of their papers we have counts for
31 papers · 1 filter
BabelSteering: Multilingual Safety Alignment via English Steering Vectors
Emma V. Stein, Dominik Meier, Terry Ruas +2
Large language models (LLMs) are deployed globally in high-stakes settings, yet most safety research and alignment efforts remain concentrated on English. Thus, users interacting w…
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
Niklas Bauer, Lars Benedikt Kaesberg, Akiko Aizawa +3
As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safe…
Who Watches the Watchmen? Humans Disagree With Translation Metrics on Unseen Domains
Finn Schmidt, Jan Philip Wahle, Terry Ruas +1
Automatic evaluation metrics are central to the development of machine translation systems, yet their robustness under domain shift remains unclear. Most metrics are developed on t…
SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA)
Liang-Chih Yu, Jonas Becker, Shamsuddeen Hassan Muhammad +14
We present the SemEval-2026 shared task on Dimensional Aspect-Based Sentiment Analysis (DimABSA), which improves traditional ABSA by modeling sentiment along valence-arousal (VA) d…
LogSigma at SemEval-2026 Task 3: Uncertainty-Weighted Multitask Learning for Dimensional Aspect-Based Sentiment Analysis
Baraa Hikal, Jonas Becker, Bela Gipp
This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA),…
Diverse Word Choices, Same Reference: Annotating Lexically-Rich Cross-Document Coreference
Anastasia Zhukova, Felix Hamborg, Karsten Donnay +2
Cross-document coreference resolution (CDCR) identifies and links mentions of the same entities and events across related documents, enabling content analysis that aggregates infor…
Piecing Together Cross-Document Coreference Resolution Datasets: Systematic Dataset Analysis and Unification
Anastasia Zhukova, Terry Ruas, Jan Philip Wahle +1
Research in CDCR remains fragmented due to heterogeneous dataset formats, varying annotation standards, and the predominance of the CDCR definition as the event coreference resolut…
DimStance: Multilingual Datasets for Dimensional Stance Analysis
Jonas Becker, Liang-Chih Yu, Shamsuddeen Hassan Muhammad +14
Stance detection is an established task that classifies an author's attitude toward a specific target into categories such as Favor, Neutral, and Against. Beyond categorical stance…
Affect, Body, Cognition, Demographics, and Emotion: The ABCDE of Text Features for Computational Affective Science
Jan Philip Wahle, Krishnapriya Vishnubhotla, Bela Gipp +1
Work in Computational Affective Science and Computational Social Science explores a wide variety of research questions about people, emotions, behavior, and health. Such work often…
Overview of the Plagiarism Detection Task at PAN 2025
André Greiner-Petter, Maik Fröbe, Jan Philip Wahle +4
The generative plagiarism detection task at PAN 2025 aims at identifying automatically generated textual plagiarism in scientific articles and aligning them with their respective s…
Contrastive Learning Using Graph Embeddings for Domain Adaptation of Language Models in the Process Industry
Anastasia Zhukova, Jonas Lührs, Christian E. Lobmüller +1
Recent trends in NLP utilize knowledge graphs (KGs) to enhance pretrained language models by incorporating additional knowledge from the graph structures to learn domain-specific t…
Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
Frederic Kirstein, Sonu Kumar, Terry Ruas +1
Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular…
Link Prediction for Event Logs in the Process Industry
Anastasia Zhukova, Thomas Walton, Christian E. Lobmüller +1
In the era of graph-based retrieval-augmented generation (RAG), link prediction is a significant preprocessing step for improving the quality of fragmented or incomplete domain-spe…
TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
Dominik Meier, Jan Philip Wahle, Paul Röttger +2
As large language models (LLMs) become integrated into sensitive workflows, concerns grow over their potential to leak confidential information. We propose TrojanStego, a novel thr…
Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language
Anastasia Zhukova, Christian E. Matt, Bela Gipp
Domain-adaptive continual pretraining (DAPT) is a state-of-the-art technique that further trains a language model (LM) on its pretraining task, e.g., masked language modeling (MLM)…
Stay Focused: Problem Drift in Multi-Agent Debate
Jonas Becker, Lars Benedikt Kaesberg, Andreas Stephan +3
Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks. Howeve…
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages
Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin +45
People worldwide use language in subtle and complex ways to express emotions. Although emotion recognition--an umbrella term for several NLP tasks--impacts various applications wit…
Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language
Anastasia Zhukova, Christian E. Matt, Bela Gipp
Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consumi…
Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator
Frederic Kirstein, Terry Ruas, Bela Gipp
The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a rel…
The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection
Tomas Horych, Christoph Mandl, Terry Ruas +4
High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests u…
Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization
Frederic Kirstein, Terry Ruas, Robert Kratel +1
Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context un…
What's Wrong? Refining Meeting Summaries with LLM Feedback
Frederic Kirstein, Terry Ruas, Bela Gipp
Meeting summarization has become a critical task since digital encounters have become a common practice. Large language models (LLMs) show great potential in summarization, offerin…
Towards Human Understanding of Paraphrase Types in Large Language Models
Dominik Meier, Jan Philip Wahle, Terry Ruas +1
Paraphrases represent a human's intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use bin…
Paraphrase Types Elicit Prompt Engineering Capabilities
Jan Philip Wahle, Terry Ruas, Yang Xu +1
Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic ex…