Towards Style Alignment in Cross-Cultural Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Havaldar, Shreya, Stein, Adam, Wong, Eric, Ungar, Lyle
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908428765495296
author Havaldar, Shreya
Stein, Adam
Wong, Eric
Ungar, Lyle
author_facet Havaldar, Shreya
Stein, Adam
Wong, Eric
Ungar, Lyle
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Style Alignment in Cross-Cultural Translation
Havaldar, Shreya
Stein, Adam
Wong, Eric
Ungar, Lyle
Computation and Language
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.
title Towards Style Alignment in Cross-Cultural Translation
topic Computation and Language
url https://arxiv.org/abs/2507.00216