# Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent

arXiv: https://arxiv.org/abs/2606.03259 · HTML: https://mlsanity.com/paper/2606.03259/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Getting Gender Right in Neural Machine Translation](https://mlsanity.com/paper/1909.05088/) (2019)
- [MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task](https://mlsanity.com/paper/2410.03983/) (2024)
- [WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects](https://mlsanity.com/paper/2502.12404/) (2025)
- [Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation](https://mlsanity.com/paper/2406.11580/) (2024)
- [MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation](https://mlsanity.com/paper/2211.01355/) (2022)
- [Controlling Text Complexity in Neural Machine Translation](https://mlsanity.com/paper/1911.00835/) (2019)
- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality](https://mlsanity.com/paper/2205.04022/) (2022)
- [BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation](https://mlsanity.com/paper/2502.04314/) (2025)
- [Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts](https://mlsanity.com/paper/2403.00127/) (2024)
- [Optimizing Machine Translation through Prompt Engineering: An Investigation into ChatGPT's Customizability](https://mlsanity.com/paper/2308.01391/) (2023)
- [Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation](https://mlsanity.com/paper/2410.20941/) (2024)
- [Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation](https://mlsanity.com/paper/2506.04521/) (2025)
- [An Interdisciplinary Approach to Human-Centered Machine Translation](https://mlsanity.com/paper/2506.13468/) (2025)
- [Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service](https://mlsanity.com/paper/2411.12262/) (2024)
- [Specification-Aware Machine Translation and Evaluation for Purpose Alignment](https://mlsanity.com/paper/2509.17559/) (2025)
- [Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation](https://mlsanity.com/paper/2604.24361/) (2026)

## Built on by (most cited first, 1 of 1)

- [Can an Old Dog Be Taught New Tricks? Taking LLMs Beyond Sentence Level Translation](https://mlsanity.com/paper/2607.14040/) (2026)

## Abstract (arXiv)

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.