paper-with-me

Papers

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

2026-06-02 · Raphael Merx, Ekaterina Vylomova, Trevor Cohn 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.

📄 PDF Abstract BibTeX arXiv:2606.03259

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Similar Papers 제목 키워드 기반

CryptoNAS: Private Inference on a ReLU Budget

2020-06-15 · NeurIPS 2020 12 · Zahra Ghodsi, Akshaj Veldanda, Brandon Reagen, Siddharth Garg

Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inp…

Tailoring Vaccine Messaging with Common-Ground Opinions

2024-05-17 · Rickard Stureborg, Sanxing Chen, Ruoyu Xie, Aayushi Patel 외

One way to personalize chatbot interactions is by establishing common ground with the intended reader. A domain where establishing mutual understanding could be particularly impactful is vaccine concerns and misinformati…

ChatbotMisinformation

Don't Overlook the Grammatical Gender: Bias Evaluation for Hindi-English Machine Translation

2023-11-11 · Pushpdeep Singh

Neural Machine Translation (NMT) models, though state-of-the-art for translation, often reflect social biases, particularly gender bias. Existing evaluation benchmarks primarily focus on English as the source language of…

Machine TranslationNMTSentenceTranslation

Hallucinations in Large Multilingual Translation Models

2023-03-28 · Nuno M. Guerreiro, Duarte Alves, Jonas Waldendorf, Barry Haddow 외

Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications. However, when de…

Language ModelingLanguage ModellingLarge Language ModelMachine Translation+1

Why We Care About Understanding: Competence through Predictive Compression

2026-09-04 · Matthieu Queloz, Pierre Beckmann arxiv

What is the relation between understanding and compression, and why does human understanding take such a heavily compressed form? Across information theory, machine learning, and AI research, a substantial tradition iden…