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

Recent advances in deep learning techniques have enabled machines to generatecohesive open-ended text when prompted with a sequence of words as context.While these models now empower many downstream applications from conversationbots to automatic storytelling, they have been shown to generate texts thatexhibit social biases. To systematically study and benchmark social biases inopen-ended language generation, we introduce the Bias in Open-Ended LanguageGeneration Dataset (BOLD), a large-scale dataset that consists of 23,679English text generation prompts for bias benchmarking across five domains:profession, gender, race, religion, and political ideology. We also propose newautomated metrics for toxicity, psycholinguistic norms, and text genderpolarity to measure social biases in open-ended text generation from multipleangles. An examination of text generated from three popular language modelsreveals that the majority of these models exhibit a larger social bias thanhuman-written Wikipedia text across all domains. With these results wehighlight the need to benchmark biases in open-ended language generation andcaution users of language generation models on downstream tasks to be cognizantof these embedded prejudices.

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation