Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent
Raphael Merx Ekaterina Vylomova Trevor Cohn
作者信息
Abstract
Translation quality depends on purpose: the same source text demands different translations depending on audience, tone, and communicative intent. Yet MT models and metrics treat translation as a fixed mapping from source to target. LLMs enable users to explicitly specify purpose alongside source text, yet this capability has not been evaluated at scale. We introduce a systematic evaluation of purpose-driven MT across 50 languages, 5 model sizes and 8 text domains. We find that (1) explicit instructions substantially improve translation adaptedness, with larger gains on informal domains (conversation, social media), for larger model sizes and for higher-resource languages; (2) instructions outperform semantically-matched few-shot examples and paragraph-level context; (3) traditional MT metrics fail to capture adaptation quality, often penalizing adapted translations; (4) when curated instructions are unavailable, models can self-generate them from surrounding document context, closing up to 80% of the adaptedness gap to curated instructions. Our results establish that purpose-adapted MT is a viable and measurable capability of LLMs, while highlighting the need for purpose-aware metrics.引用本文复制引用
Raphael Merx,Ekaterina Vylomova,Trevor Cohn.Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent[EB/OL].(2026-06-02)[2026-06-06].https://arxiv.org/abs/2606.03259.学科分类
语言学/常用外国语
|国家预印本平台