LLMs Out-of-the-Box Do Not Generate Context-Appropriate Word Order in Russian

Alina Shabaeva, John Frederick Bailyn, Owen Rambow


Abstract
In this paper, we examine whether LLMs can generate context-appropriate word order in Russian. Using a new corpus of movie scripts in Russian, with a particular focus on dialogues, we investigate how various semantic, morphosyntactic, and discourse features influence word order choice. We show that traditional machine learning can use these features to model different word order fairly well. We also examine whether LLM dialogue partners can generate context-appropriate word order in Russian. With both zero- and few-shot prompting, LLMs fail to generate word orders beyond the default subject-verb-object. Instead, in order to generate context-appropriate word orders, LLMs need to be fine-tuned or given explicit word order suggestions from a traditional machine learning method.
Anthology ID:
2026.sigdial-1.32
Volume:
Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
August
Year:
2026
Address:
Atlanta, Georgia, USA
Editors:
Jinho D. Choi, Yun-Nung Chen, Kotaro Funakoshi, Ali Emami
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
453–472
Language:
URL:
https://aclanthology.org/2026.sigdial-1.32/
DOI:
Bibkey:
Cite (ACL):
Alina Shabaeva, John Frederick Bailyn, and Owen Rambow. 2026. LLMs Out-of-the-Box Do Not Generate Context-Appropriate Word Order in Russian. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 453–472, Atlanta, Georgia, USA. Association for Computational Linguistics.
Cite (Informal):
LLMs Out-of-the-Box Do Not Generate Context-Appropriate Word Order in Russian (Shabaeva et al., SIGDIAL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.sigdial-1.32.pdf