Paper

Student Chatbot Marcel (EMNLP'25)

  • nlp
  • education

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 ...

Paper

Annotation-Free Breast Cancer Prediction (CBM)

  • computer vision
  • medicine

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...

Paper

Probing Information Salience (ACL'25)

  • nlp

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...

Paper

Unlearning Spurious Correlations (TMLR)

  • representation learning
  • computer vision

“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, ...

Paper

LLMs for Counterfactuals (EMNLP'24)

  • nlp

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...

Project

Start of the DFG project HEAR

  • computer vision
  • XAI
  • medicine

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...

Award

PhD Award Meike Nauta

  • XAI

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,...

Paper

Fact Retrieval from LLMs (EMNLP'23)

  • nlp
  • survey

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...

Paper

PIP-Net - Interpretable Computer Vision (CVPR'23)

  • computer vision
  • explainable AI

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...