News
Transparency in Bayesian Optimization
On May 5th, Tanmay Chakraborty successfully defended his doctoral thesis on explainability and human–algorithm collaboration in Bayesian Optimization. His research addresses a key challenge in industrial optimization:...
Tracing and Reversing Edits in LLMs (ICLR'26)
Knowledge editing is used to update large language models when facts change. Instead of retraining an entire model, editing methods can directly modify the model’s parameters so that it responds with new information. ...
Content Selection in Text Summarization and Simplification
On December 17th, Jan Trienes successfully defended his PhD thesis. Over the past years, he investigated content selection in large language models (LLMs). While NLP tasks such as automatic text summarization and simp...
Student Chatbot Marcel (EMNLP'25)
At this year’s EMNLP in Suzhou, China, Jan Trienes presented Marcel, a RAG-based conversational agent built to handle enrollment questions at Marburg University (Trienes et al., 2025). The project grew out of a simple...
Student Initiative Receives Hessian Teaching Award
The AI-Lab: AI & Society project has been awarded the Hessian University Teaching Prize! This recognition reflects the passion, creativity, and hard work of everyone involved—especially the student leaders who tur...
Annotation-Free Breast Cancer Prediction (CBM)
Most AI models for breast cancer detection assume that each mammogram image, or even each region within an image, has been manually labeled. However, in real hospitals, clinicians only provide a final, case-level diag...
Bridging the Gap Between AI Research and Real-World Healthcare
On September 6, 2025, Shreyasi Pathak successfully defended her PhD thesis at the University of Twente, marking a significant step forward in the practical application of AI in everyday healthcare. Conducted in collab...
Probing Information Salience (ACL'25)
Jan Trienes presented research at ACL 2025 in Vienna on how large language models (LLMs) identify important information in text. Using text summarization as a probe, we discovered that while LLMs demonstrate a consis...
Unlearning Spurious Correlations (TMLR)
“This is a cow, because the background is a meadow.” Machine learning models often rely on spurious correlations — features that are strongly associated with class labels but lack any causal connection. For example, ...
Knowledge Editing in Large Language Models (ICML, NAACL'25)
In our ever-changing world, the knowledge stored in large language models (LLMs) must be continuously updated as facts evolve. The president of the U.S. is … Knowledge Editing One way of “teaching” new informat...
LLMs for Counterfactuals (EMNLP'24)
What minimal changes to this text would cause the text classifier to change its prediction? Counterfactual texts, i.e. minimal changes to inputs that alter a model’s predictions, are an important technique in Exp...
Start of the DFG project HEAR
What is the potential hearing gain after cochlear implantation? Cochlear implants have been successfully implanted in patients with deafness or severe hearing loss, enabling them to perceive sound and thereby acqui...
InfoLossQA: Information Loss in Text Simplification (ACL'24)
How can we recover what has been lost in text simplification? Text simplification aims to make texts more accessible to a broader audience. Simplification, however, is inherently a lossy process. Additionally, one si...
PhD Award Meike Nauta
Meike Nauta has been awarded the Overijssel PhD Award for her outstanding dissertation, “Explainable AI and Interpretable Computer Vision – From Oversight to Insight.” The award recognizes Nauta’s innovative research,...
Start of the Marflex Project Marcel, a Chatbot for Students
The MarFlex initiative aims to make study programs more flexible. Under this umbrella, we will develop Marcel (Marburger Study Accelerator), a chatbot to assist students with their questions around study programs, an...
'The Queen of England is not England’s Queen.' (EACL'24)
When humans know “Rome is the capital of Italy”, they also know “The capital of Italy is Rome”. This means, if humans know a fact, they can be either queried for the subject or the object of the relation and retrieve...
Start of the Pioneers in Healthcare project ReBreCa
Pioneers in Healthcare is an innovation fund awarded by University of Twente, Saxion, MST, ZGT and Deventer Hospital. It awards projects with impact on health care aiming to foster long-standing collaboration. Our p...
Fact Retrieval from LLMs (EMNLP'23)
How do we know what Language Models know? And what are obstacles in using them as knowledge bases? In our recent paper presented at EMNLP, we survey methods and datasets for probing PLMs along a categorization scheme...
PIP-Net - Interpretable Computer Vision (CVPR'23)
Interpretable methods using prototypical patches help AI explain its reasoning to humans. However, current prototype-based methods may not align with human visual perception, resulting in non-intuitive interpretation...