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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Language models (LMs) have achieved notable success in numerous NLP tasks,employing both fine-tuning and in-context learning (ICL) methods. Whilelanguage models demonstrate exceptional performance, they face robustnesschallenges due to spurious correlations arising from imbalanced labeldistributions in training data or ICL exemplars. Previous research hasprimarily concentrated on word, phrase, and syntax features, neglecting theconcept level, often due to the absence of concept labels and difficulty inidentifying conceptual content in input texts. This paper introduces two maincontributions. First, we employ ChatGPT to assign concept labels to texts,assessing concept bias in models during fine-tuning or ICL on test data. Wefind that LMs, when encountering spurious correlations between a concept and alabel in training or prompts, resort to shortcuts for predictions. Second, weintroduce a data rebalancing technique that incorporates ChatGPT-generatedcounterfactual data, thereby balancing label distribution and mitigatingspurious correlations. Our method's efficacy, surpassing traditional tokenremoval approaches, is validated through extensive testing.

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification