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

Multilingual generative language models (LMs) are increasingly fluent in alarge variety of languages. Trained on the concatenation of corpora in multiplelanguages, they enable powerful transfer from high-resource languages tolow-resource ones. However, it is still unknown what cultural biases areinduced in the predictions of these models. In this work, we focus on onelanguage property highly influenced by culture: formality. We analyze theformality distributions of XGLM and BLOOM's predictions, two popular generativemultilingual language models, in 5 languages. We classify 1,200 generations perlanguage as formal, informal, or incohesive and measure the impact of theprompt formality on the predictions. Overall, we observe a diversity ofbehaviors across the models and languages. For instance, XGLM generatesinformal text in Arabic and Bengali when conditioned with informal prompts,much more than BLOOM. In addition, even though both models are highly biasedtoward the formal style when prompted neutrally, we find that the modelsgenerate a significant amount of informal predictions even when prompted withformal text. We release with this work 6,000 annotated samples, paving the wayfor future work on the formality of generative multilingual LMs.

In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages