4 citations · 22 across the 35 of their papers we have counts for
36 papers
Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review
Louis Peter, Nils Gumpfer, Jana Fischer +2
Time series arise in a wide range of application domains and are analyzed using machine learning in decision-critical settings. Time series classification (TSC) is one of the most…
Persuasion Tokens for Editing Factual Knowledge in LLMs
Paul Youssef, Christin Seifert, Jörg Schlötterer
In-context knowledge editing (IKE) is a promising technique for updating Large Language Models (LLMs) with new information. However, IKE relies on lengthy, fact-specific demonstrat…
XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
Khawla Elhadri, Jörg Schlötterer, Christin Seifert
In data-driven applications relying on tabular data, where interpretability is key, machine learning models such as decision trees and linear regression are applied. Although neura…
Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
Yinjie Cheng, Paul Youssef, Christin Seifert +2
Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting L…
Towards Interpretable Deep Neural Networks for Tabular Data
Khawla Elhadri, Jörg Schlötterer, Christin Seifert
Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, th…
Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support
Jan Trienes, Anastasiia Derzhanskaia, Roland Schwarzkopf +3
We present Marcel, a lightweight and open-source conversational agent designed to support prospective students with admission-related inquiries. The system aims to provide fast and…
Tracing and Reversing Edits in LLMs
Paul Youssef, Zhixue Zhao, Christin Seifert +1
Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for…
Invariant Learning with Annotation-free Environments
Phuong Quynh Le, Christin Seifert, Jörg Schlötterer
Invariant learning is a promising approach to improve domain generalization compared to Empirical Risk Minimization (ERM). However, most invariant learning methods rely on the assu…
An XAI-based Analysis of Shortcut Learning in Neural Networks
Phuong Quynh Le, Jörg Schlötterer, Christin Seifert
Machine learning models tend to learn spurious features - features that strongly correlate with target labels but are not causal. Existing approaches to mitigate models' dependence…
Guiding LLMs to Generate High-Fidelity and High-Quality Counterfactual Explanations for Text Classification
Van Bach Nguyen, Christin Seifert, Jörg Schlötterer
The need for interpretability in deep learning has driven interest in counterfactual explanations, which identify minimal changes to an instance that change a model's prediction. C…
Behavioral Analysis of Information Salience in Large Language Models
Jan Trienes, Jörg Schlötterer, Junyi Jessy Li +1
Large Language Models (LLMs) excel at text summarization, a task that requires models to select content based on its importance. However, the exact notion of salience that LLMs hav…
This looks like what? Challenges and Future Research Directions for Part-Prototype Models
Khawla Elhadri, Tomasz Michalski, Adam Wróbel +3
The growing interest in eXplainable Artificial Intelligence (XAI) has stimulated research on models with built-in interpretability, among which part-prototype models are particular…
Position: Editing Large Language Models Poses Serious Safety Risks
Paul Youssef, Zhixue Zhao, Daniel Braun +2
Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing method…
Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
Lukas Kuhn, Sari Sadiya, Jorg Schlotterer +3
Shortcut learning, i.e., a model's reliance on undesired features not directly relevant to the task, is a major challenge that severely limits the applications of machine learning…
Enhancing Fact Retrieval in PLMs through Truthfulness
Paul Youssef, Jörg Schlötterer, Christin Seifert
Pre-trained Language Models (PLMs) encode various facts about the world at their pre-training phase as they are trained to predict the next or missing word in a sentence. There has…
How to Make LLMs Forget: On Reversing In-Context Knowledge Edits
Paul Youssef, Zhixue Zhao, Jörg Schlötterer +1
In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to ma…
Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine
Bahadır Eryılmaz, Osman Alperen Koraş, Jörg Schlötterer +1
Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often un…
Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classification
Lisa Anita De Santi, Jörg Schlötterer, Meike Nauta +2
Volumetric neuroimaging examinations like structural Magnetic Resonance Imaging (sMRI) are routinely applied to support the clinical diagnosis of dementia like Alzheimer's Disease…
Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
Phuong Quynh Le, Jörg Schlötterer, Christin Seifert
Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations lea…
Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding
Ahmad Idrissi-Yaghir, Amin Dada, Henning Schäfer +17
Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate…
Has this Fact been Edited? Detecting Knowledge Edits in Language Models
Paul Youssef, Zhixue Zhao, Christin Seifert +1
Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., i…
LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study
Van Bach Nguyen, Paul Youssef, Christin Seifert +1
As NLP models become more complex, understanding their decisions becomes more crucial. Counterfactuals (CFs), where minimal changes to inputs flip a model's prediction, offer a way…
Feature importance to explain multimodal prediction models. A clinical use case
Jorn-Jan van de Beld, Shreyasi Pathak, Jeroen Geerdink +2
Surgery to treat elderly hip fracture patients may cause complications that can lead to early mortality. An early warning system for complications could provoke clinicians to monit…
CEval: A Benchmark for Evaluating Counterfactual Text Generation
Van Bach Nguyen, Jörg Schlötterer, Christin Seifert
Counterfactual text generation aims to minimally change a text, such that it is classified differently. Judging advancements in method development for counterfactual text generatio…