Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent
cs.CL
Submitted: 2026-06-02
Updated: 2026-08-31
Comments: Accepted at EMNLP 2026 main
License: http://creativecommons.org/licenses/by/4.0/
The gist: Translation quality depends on purpose: the same source text demands different translations depending on audience, tone, and communicative intent.
Terminology
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.
Sources
- Gemma 3 Technical Report
- LoRA: Low-Rank Adaptation of Large Language Models
- New Trends for Modern Machine Translation with Large Reasoning Models
- No Language Left Behind: Scaling Human-Centered Machine Translation
- Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
- Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering