# Translating Under Pressure: Domain-Aware LLMs for Crisis Communication

arXiv: https://arxiv.org/abs/2604.26597 · HTML: https://mlsanity.com/paper/2604.26597/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [CrisisMMD: Multimodal Twitter Datasets from Natural Disasters](https://mlsanity.com/paper/1805.00713/) (2018)
- [TICO-19: the Translation Initiative for Covid-19](https://mlsanity.com/paper/2007.01788/) (2020)
- [How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes](https://mlsanity.com/paper/2409.03454/) (2024)
- [Pearmut: Human Evaluation of Translation Made Trivial](https://mlsanity.com/paper/2601.02933/) (2026)
- [An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification](https://mlsanity.com/paper/1704.05415/) (2017)
- [Synergistic Union of Word2Vec and Lexicon for Domain Specific Semantic Similarity](https://mlsanity.com/paper/1706.01967/) (2017)
- [A Resource-Light Method for Cross-Lingual Semantic Textual Similarity](https://mlsanity.com/paper/1801.06436/) (2018)

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

- [SIREN: Situation-aware Index for Response and Emergency ActioNability in Crisis Translation](https://mlsanity.com/paper/2610.16646/) (2026)

## Abstract (arXiv)

Timely and reliable multilingual communication is critical during natural and human-induced disasters, but developing effective solutions for crisis communication is limited by the scarcity of curated parallel data. We propose a domain-adaptive pipeline that expands a small reference corpus, by retrieving and filtering data from general corpora. We use the resulting dataset to fine-tune a small language model for crisis-domain translation and then apply preference optimization to bias outputs toward CEFR A2-level English. Automatic and human evaluation shows that this approach improves readability, while maintaining strong adequacy. Our results indicate that simplified English, combined with domain adaptation, can function as a practical lingua franca for emergency communication when full multilingual coverage is not feasible.