English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent research has shown that large language models rely on spuriouscorrelations in the data for natural language understanding (NLU) tasks. Inthis work, we aim to answer the following research question: Can we reducespurious correlations by modifying the ground truth labels of the trainingdata? Specifically, we propose a simple yet effective debiasing framework,named Soft Label Encoding (SoftLE). We first train a teacher model with hardlabels to determine each sample's degree of relying on shortcuts. We then addone dummy class to encode the shortcut degree, which is used to smooth otherdimensions in the ground truth label to generate soft labels. This new groundtruth label is used to train a more robust student model. Extensive experimentson two NLU benchmark tasks demonstrate that SoftLE significantly improvesout-of-distribution generalization while maintaining satisfactoryin-distribution accuracy.

Mitigating Shortcuts in Language Models with Soft Label Encoding