{"ID":3005035,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T07:16:01.131756733Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03259","arxiv_id":"2606.03259","title":"Beyond \"To whom it may concern\": Tailoring Machine Translation to Audience and Intent","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.","short_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 capabil...","url_abs":"https://arxiv.org/abs/2606.03259","url_pdf":"https://arxiv.org/pdf/2606.03259v1","authors":"[\"Raphael Merx\",\"Ekaterina Vylomova\",\"Trevor Cohn\"]","published":"2026-06-02T07:23:01Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}