10 citations · 51 across the 23 of their papers we have counts for
25 papers
When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings
Christopher Schröder, Lukas Gienapp, Ferdinand Schlatt +2
We identify a previously overlooked failure mode of ALiBi positional encoding: its linear bias scaling underflows floating-point precision, which zeroes out a large fraction of att…
Data Annotations as Pedagogical Hints: From Subjective Labels to Critical Thinking
Ralf Raumanns, Theresa Elstner, Louis Ferger-Andrews +5
Machine learning courses often use pre-labelled datasets, hiding the subjectivity of human annotation. This produces an overly trusting view of data and AI models in students, at t…
Detecting RAG Advertisements Across Advertising Styles
Sebastian Heineking, Wilhelm Pertsch, Ines Zelch +4
Large language models (LLMs) enable a new form of advertising for retrieval-augmented generation (RAG) systems in which organic responses are blended with contextually relevant ads…
Representation Fidelity:Auditing Algorithmic Decisions About Humans Using Self-Descriptions
Theresa Elstner, Martin Potthast
This paper introduces a new dimension for validating algorithmic decisions about humans by measuring the fidelity of their representations. Representation Fidelity measures if deci…
Overview of PAN 2026: Voight-Kampff Generative AI Detection, Text Watermarking, Multi-Author Writing Style Analysis, Generative Plagiarism Detection, and Reasoning Trajectory Detection
Janek Bevendorff, Maik Fröbe, André Greiner-Petter +9
The goal of the PAN workshop is to advance computational stylometry and text forensics via objective and reproducible evaluation. In 2026, we run the following five tasks: (1) Voig…
The German Commons - 154 Billion Tokens of Openly Licensed Text for German Language Models
Lukas Gienapp, Christopher Schröder, Stefan Schweter +5
Large language model development relies on large-scale training corpora, yet most contain data of unclear licensing status, limiting the development of truly open models. This prob…
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…
Investigating Counterclaims in Causality Extraction from Text
Tim Hagen, Niklas Deckers, Felix Wolter +2
Many causal claims, such as "sugar causes hyperactivity," are disputed or outdated. Yet research on causality extraction from text has almost entirely neglected counterclaims of ca…
Topic-Specific Classifiers are Better Relevance Judges than Prompted LLMs
Lukas Gienapp, Martin Potthast, Andrew Yates +2
The unjudged document problem, where systems that did not contribute to the original judgement pool may retrieve documents without a relevance judgement, is a key obstacle to the r…
Simplified Longitudinal Retrieval Experiments: A Case Study on Query Expansion and Document Boosting
Jüri Keller, Maik Fröbe, Gijs Hendriksen +3
The longitudinal evaluation of retrieval systems aims to capture how information needs and documents evolve over time. However, classical Cranfield-style retrieval evaluations only…
The Viability of Crowdsourcing for RAG Evaluation
Lukas Gienapp, Tim Hagen, Maik Fröbe +4
How good are humans at writing and judging responses in retrieval-augmented generation (RAG) scenarios? To answer this question, we investigate the efficacy of crowdsourcing for RA…
AiReview: An Open Platform for Accelerating Systematic Reviews with LLMs
Xinyu Mao, Teerapong Leelanupab, Martin Potthast +2
Systematic reviews are fundamental to evidence-based medicine. Creating one is time-consuming and labour-intensive, mainly due to the need to screen, or assess, many studies for in…
Counterfactual Query Rewriting to Use Historical Relevance Feedback
Jüri Keller, Maik Fröbe, Gijs Hendriksen +4
When a retrieval system receives a query it has encountered before, previous relevance feedback, such as clicks or explicit judgments can help to improve retrieval results. However…
Ranking Generated Answers: On the Agreement of Retrieval Models with Humans on Consumer Health Questions
Sebastian Heineking, Jonas Probst, Daniel Steinbach +2
Evaluating the output of generative large language models (LLMs) is challenging and difficult to scale. Many evaluations of LLMs focus on tasks such as single-choice question-answe…
Systematic Evaluation of Neural Retrieval Models on the Touché 2020 Argument Retrieval Subset of BEIR
Nandan Thakur, Luiz Bonifacio, Maik Fröbe +5
The zero-shot effectiveness of neural retrieval models is often evaluated on the BEIR benchmark -- a combination of different IR evaluation datasets. Interestingly, previous studie…
Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins
Lukas Gienapp, Niklas Deckers, Martin Potthast +1
Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current…
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren +3
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple cali…
Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
Ferdinand Schlatt, Maik Fröbe, Harrisen Scells +6
Cross-encoders distilled from large language models (LLMs) are often more effective re-rankers than cross-encoders fine-tuned on manually labeled data. However, distilled models do…
If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level
Matti Wiegmann, Jennifer Rakete, Magdalena Wolska +2
Trigger warnings are labels that preface documents with sensitive content if this content could be perceived as harmful by certain groups of readers. Since warnings about a documen…
Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
Ferdinand Schlatt, Maik Fröbe, Harrisen Scells +6
Existing cross-encoder models can be categorized as pointwise, pairwise, or listwise. Pairwise and listwise models allow passage interactions, which typically makes them more effec…
Task-Oriented Paraphrase Analytics
Marcel Gohsen, Matthias Hagen, Martin Potthast +1
Since paraphrasing is an ill-defined task, the term "paraphrasing" covers text transformation tasks with different characteristics. Consequently, existing paraphrasing studies have…
Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
Andrew Parry, Maik Fröbe, Sean MacAvaney +2
Modern sequence-to-sequence relevance models like monoT5 can effectively capture complex textual interactions between queries and documents through cross-encoding. However, the use…
Detecting Generated Native Ads in Conversational Search
Sebastian Schmidt, Ines Zelch, Janek Bevendorff +3
Conversational search engines such as YouChat and Microsoft Copilot use large language models (LLMs) to generate responses to queries. It is only a small step to also let the same…
Zero-shot Generative Large Language Models for Systematic Review Screening Automation
Shuai Wang, Harrisen Scells, Shengyao Zhuang +3
Systematic reviews are crucial for evidence-based medicine as they comprehensively analyse published research findings on specific questions. Conducting such reviews is often resou…