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

Pretrained language models (PLM) achieve surprising performance on the Choiceof Plausible Alternatives (COPA) task. However, whether PLMs have trulyacquired the ability of causal reasoning remains a question. In this paper, weinvestigate the problem of semantic similarity bias and reveal thevulnerability of current COPA models by certain attacks. Previous solutionsthat tackle the superficial cues of unbalanced token distribution stillencounter the same problem of semantic bias, even more seriously due to theutilization of more training data. We mitigate this problem by simply adding aregularization loss and experimental results show that this solution not onlyimproves the model's generalization ability, but also assists the models toperform more robustly on a challenging dataset, BCOPA-CE, which has unbiasedtoken distribution and is more difficult for models to distinguish cause andeffect.

Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models