Towards Style Alignment in Cross-Cultural Translation
This addresses style communication issues in translation for users across cultures, but it is incremental as it builds on existing LLM methods.
The paper tackles the problem of style misalignment in cross-cultural translation due to cultural differences, such as politeness loss, by introducing RASTA, a retrieval-augmented method that improves LLM translation to convey cultural norms, achieving better style alignment.
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.