16 papers
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…
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…
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…
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…
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…
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…