Papers › Discovering Language-neutral Sub-networks in Multilingual Language Models

Discovering Language-neutral Sub-networks in Multilingual Language Models

25 May 2022arXiv:2205.12672archive 2025-07-28

Negar Foroutan, Mohammadreza Banaei, Remi Lebret, Antoine Bosselut, Karl Aberer

Multilingual pre-trained language models transfer remarkably well on cross-lingual downstream tasks. However, the extent to which they learn language-neutral representations (i.e., shared representations that encode similar phenomena across languages), and the effect of such representations on cross-lingual transfer performance, remain open questions. In this work, we conceptualize language neutrality of multilingual models as a function of the overlap between language-encoding sub-networks of these models. We employ the lottery ticket hypothesis to discover sub-networks that are individually optimized for various languages and tasks. Our evaluation across three distinct tasks and eleven typologically-diverse languages demonstrates that sub-networks for different languages are topologically similar (i.e., language-neutral), making them effective initializations for cross-lingual transfer with limited performance degradation.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

negar-foroutan/multiLMs-lang-neutral-subnets officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Lingual Transfer

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

mBERT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections