Towards Style Alignment in Cross-Cultural Translation
Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar
Abstract
Successful communication depends on the speaker’s intended style (i.e., what the speaker is trying to convey) aligning with the listener’s interpreted style (i.e., what the listener perceives). However, cultural differences often lead to misalignment between the two; for example, politeness is often lost in translation. We characterize the ways that LLMs fail to translate style – biasing translations towards neutrality and performing worse in non-Western languages. We mitigate these failures with RASTA (Retrieval-Augmented STylistic Alignment), a method that leverages learned stylistic concepts to encourage LLM translation to appropriately convey cultural communication norms and align style.
BibTeX
@inproceedings{havaldar-etal-2025-towards,
title = "Towards Style Alignment in Cross-Cultural Translation",
author = "Havaldar, Shreya and
Stein, Adam and
Wong, Eric and
Ungar, Lyle",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1550/",
doi = "10.18653/v1/2025.acl-long.1550",
pages = "32213--32230",
ISBN = "979-8-89176-251-0"
}