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 work has proposed explicitly inducing language-wise modularity inmultilingual LMs via sparse fine-tuning (SFT) on per-language subnetworks as ameans of better guiding cross-lingual sharing. In this work, we investigate (1)the degree to which language-wise modularity naturally arises within modelswith no special modularity interventions, and (2) how cross-lingual sharing andinterference differ between such models and those with explicit SFT-guidedsubnetwork modularity. To quantify language specialization and cross-lingualinteraction, we use a Training Data Attribution method that estimates thedegree to which a model's predictions are influenced by in-language orcross-language training examples. Our results show that language-specializedsubnetworks do naturally arise, and that SFT, rather than always increasingmodularity, can decrease language specialization of subnetworks in favor ofmore cross-lingual sharing.

Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks