Zobrazeno 1 - 10
of 336
pro vyhledávání: '"SEIFERT, CHRISTIN"'
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 a been an interest in quantifying and improving the amount of facts t
Externí odkaz:
http://arxiv.org/abs/2410.13562
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 manipulate responses opaquely, e.g., insert misinformation or offensive
Externí odkaz:
http://arxiv.org/abs/2410.12586
Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantag
Externí odkaz:
http://arxiv.org/abs/2410.02806
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 leads to poor performance in the data groups without these correlations a
Externí odkaz:
http://arxiv.org/abs/2407.14974
Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classification
Volumetric neuroimaging examinations like structural Magnetic Resonance Imaging (sMRI) are routinely applied to support the clinical diagnosis of dementia like Alzheimer's Disease (AD). Neuroradiologists examine 3D sMRI to detect and monitor abnormal
Externí odkaz:
http://arxiv.org/abs/2407.14277
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., inserting misinformation and toxic content. Knowing whether a generated
Externí odkaz:
http://arxiv.org/abs/2405.02765
Autor:
van de Beld, Jorn-Jan, Pathak, Shreyasi, Geerdink, Jeroen, Hegeman, Johannes H., Seifert, Christin
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 monitor high-risk patients more carefully and address potential complicatio
Externí odkaz:
http://arxiv.org/abs/2404.18631
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 to explain these models. While Large Language Models (LLMs) have show
Externí odkaz:
http://arxiv.org/abs/2405.00722
Publikováno v:
INLG 2024
Counterfactual text generation aims to minimally change a text, such that it is classified differently. Judging advancements in method development for counterfactual text generation is hindered by a non-uniform usage of data sets and metrics in relat
Externí odkaz:
http://arxiv.org/abs/2404.17475
Autor:
Idrissi-Yaghir, Ahmad, Dada, Amin, Schäfer, Henning, Arzideh, Kamyar, Baldini, Giulia, Trienes, Jan, Hasin, Max, Bewersdorff, Jeanette, Schmidt, Cynthia S., Bauer, Marie, Smith, Kaleb E., Bian, Jiang, Wu, Yonghui, Schlötterer, Jörg, Zesch, Torsten, Horn, Peter A., Seifert, Christin, Nensa, Felix, Kleesiek, Jens, Friedrich, Christoph M.
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 remarkable performance on general datasets, they can struggle in spec
Externí odkaz:
http://arxiv.org/abs/2404.05694