Unlearning spurious correlations (TMLR)
Machine learning models often rely on spurious correlations — features that are strongly associated with class labels but lack any causal connection. For exa...
Machine learning models often rely on spurious correlations — features that are strongly associated with class labels but lack any causal connection. For exa...
In our ever-changing world, knowledge of language models (LLMs) needs to be constantly updated. Facts change and LLMs need to reflect this.
“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...
Text simplification aims to make texts more accessible to a broader audience. Simplification, however, is inherently a lossy process. Additionally, one simpl...