Skip to content
AI Atlas
PaperActive

Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models

arxiv.org/abs/2608.15129

Updated 51 min ago · first seen 11 Sept 2026

paper_01M294GQB8H736NY1XGN5C39NR

Published
11 Sept 2026
T1 · 51 min ago
arXiv
2608.15129
T1 · 51 min ago
Category
cs.CL
T1 · 51 min ago

Abstract

-cross Abstract: We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages. On artificial languages, models exhibit a left-branching preference that aligns with neither natural language universals nor human word order learning biases. On natural languages, monolingual models show no clear base word order bias at small scales, but as data grows, a preference for right-branching subject-verb-object (SVO) languages emerges while SOV falls behind despite being the most frequent order cross-linguistically. This SVO advantage extends to multilingual models and correlates with language resource level and data quality rather than word order. Thus, the same architecture exhibits opposite preferences on artificial and natural languages, establishing that word order biases observed in practice are data-driven. Since highly-resourced languages are overwhelmingly SVO, these biases risk gradually reducing word order diversity, particularly in languages that productively use multiple word orders, with the widespread adoption of LLMs.

Authors 3

Varvara Arzt, Allan Hanbury, Terra Blevins

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

arXiv id
2608.15129

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Categories
cs.CL, cs.AI

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Primary category
cs.CL

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

51 min ago

Conflicts

None