125 citations · 367 across the 35 of their papers we have counts for
37 papers
AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models
Andreas Einwiller, Max Klabunde, Florian Lemmerich
The worldwide rise of authoritarianism and the growing role of Large Language Models (LLMs) in users' everyday lives raise the question of whether specific models exhibit or promot…
A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
Steffen Herbold, Florian Lemmerich
The generation of texts using Large Language Models (LLMs) is inherently uncertain, with sources of uncertainty being not only the generation of texts, but also the prompt used and…
Form Without Function: Agent Social Behavior in the Moltbook Network
Saber Zerhoudi, Kanishka Ghosh Dastidar, Felix Klement +9
Moltbook is a social network where every participant is an AI agent. We analyze 1,312,238 posts, 6.7~million comments, and over 120,000 agent profiles across 5,400 communities, col…
Behind the Prompt: The Agent-User Problem in Information Retrieval
Saber Zerhoudi, Michael Granitzer, Dang Hai Dang +5
User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately confi…
Benevolent Dictators? On LLM Agent Behavior in Dictator Games
Andreas Einwiller, Kanishka Ghosh Dastidar, Artur Romazanov +3
In behavioral sciences, experiments such as the ultimatum game are conducted to assess preferences for fairness or self-interest of study participants. In the dictator game, a simp…
Revisiting the Relation Between Robustness and Universality
M. Klabunde, L. Caspari, F. Lemmerich
The modified universality hypothesis proposed by Jones et al. (2022) suggests that adversarially robust models trained for a given task are highly similar. We revisit the hypothesi…
Linearity-based neural network compression
Silas Dobler, Florian Lemmerich
In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we…
SubROC: AUC-Based Discovery of Exceptional Subgroup Performance for Binary Classifiers
Tom Siegl, Kutalmış Coşkun, Bjarne C. Hiller +3
Machine learning (ML) is increasingly employed in real-world applications like medicine or economics, thus, potentially affecting large populations. However, ML models often do not…
ReSi: A Comprehensive Benchmark for Representational Similarity Measures
Max Klabunde, Tassilo Wald, Tobias Schumacher +3
Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper pr…
Towards Measuring Representational Similarity of Large Language Models
Max Klabunde, Mehdi Ben Amor, Michael Granitzer +1
Understanding the similarity of the numerous released large language models (LLMs) has many uses, e.g., simplifying model selection, detecting illegal model reuse, and advancing ou…
Similarity of Neural Network Models: A Survey of Functional and Representational Measures
Max Klabunde, Tobias Schumacher, Markus Strohmaier +1
Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest. In this survey, we provide a compreh…
On the Prediction Instability of Graph Neural Networks
Max Klabunde, Florian Lemmerich
Instability of trained models, i.e., the dependence of individual node predictions on random factors, can affect reproducibility, reliability, and trust in machine learning systems…
Updating Embeddings for Dynamic Knowledge Graphs
Christopher Wewer, Florian Lemmerich, Michael Cochez
Data in Knowledge Graphs often represents part of the current state of the real world. Thus, to stay up-to-date the graph data needs to be updated frequently. To utilize informatio…
Redescription Model Mining
Felix I. Stamm, Martin Becker, Markus Strohmaier +1
This paper introduces Redescription Model Mining, a novel approach to identify interpretable patterns across two datasets that share only a subset of attributes and have no common…
Surfacing Estimation Uncertainty in the Decay Parameters of Hawkes Processes with Exponential Kernels
Tiago Santos, Florian Lemmerich, Denis Helic
As a tool for capturing irregular temporal dependencies (rather than resorting to binning temporal observations to construct time series), Hawkes processes with exponential decay h…
A Comparative Evaluation of Quantification Methods
Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
Quantification represents the problem of estimating the distribution of class labels on unseen data. It also represents a growing research field in supervised machine learning, for…
The FairCeptron: A Framework for Measuring Human Perceptions of Algorithmic Fairness
Georg Ahnert, Ivan Smirnov, Florian Lemmerich +2
Measures of algorithmic fairness often do not account for human perceptions of fairness that can substantially vary between different sociodemographics and stakeholders. The FairCe…
Volunteer contributions to Wikipedia increased during COVID-19 mobility restrictions
Thorsten Ruprechter, Manoel Horta Ribeiro, Tiago Santos +4
Wikipedia, the largest encyclopedia ever created, is a global initiative driven by volunteer contributions. When the COVID-19 pandemic broke out and mobility restrictions ensued ac…
From Asking to Answering: Getting More Involved on Stack Overflow
Timur Bachschi, Aniko Hannak, Florian Lemmerich +1
Online knowledge platforms such as Stack Overflow and Wikipedia rely on a large and diverse contributor community. Despite efforts to facilitate onboarding of new users, relatively…
Simulating systematic bias in attributed social networks and its effect on rankings of minority nodes
Felix I. Stamm, Leonie Neuhäuser, Florian Lemmerich +2
Network analysis provides powerful tools to learn about a variety of social systems. However, most analyses implicitly assume that the considered relational data is error-free, rel…
Global gender differences in Wikipedia readership
Isaac Johnson, Florian Lemmerich, Diego Sáez-Trumper +3
Wikipedia represents the largest and most popular source of encyclopedic knowledge in the world today, aiming to provide equal access to information worldwide. From a global online…
Quota-based debiasing can decrease representation of already underrepresented groups
Ivan Smirnov, Florian Lemmerich, Markus Strohmaier
Many important decisions in societies such as school admissions, hiring, or elections are based on the selection of top-ranking individuals from a larger pool of candidates. This p…
The Effects of Randomness on the Stability of Node Embeddings
Tobias Schumacher, Hinrikus Wolf, Martin Ritzert +6
We systematically evaluate the (in-)stability of state-of-the-art node embedding algorithms due to randomness, i.e., the random variation of their outcomes given identical algorith…
Sudden Attention Shifts on Wikipedia During the COVID-19 Crisis
Manoel Horta Ribeiro, Kristina Gligorić, Maxime Peyrard +3
We study how the COVID-19 pandemic, alongside the severe mobility restrictions that ensued, has impacted information access on Wikipedia, the world's largest online encyclopedia. A…