Newest papers

CrisiLangs: A Multilingual Resource for Crisis Warning Generation

Giacomo Gonella, Stefano Menini, Marco Guerini · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31356 · cited by 0 works (OpenAlex) · open-access PDF

Korean

응급 상황에서 대중과 통신하는 것은 신속하게 경고 메시지를 발행하는 것을 의미합니다. 유럽에서는 종종 그 메시지를 하나 이상의 언어로 생성하는 것이 필요합니다. 최근의 연구는 언어 모델이 위기가 발생할 때 경고 메시지를 생성하도록 훈련받을 수 있음을 보여주었습니다. 그러나 사용 가능한 데이터는 영어로만 커버합니다. 이 격차를 채우기 위해 CrisiLangs는 5 개 언어에 걸쳐 5,000 개의 이벤트 메시지 쌍을 제공합니다. 우리는 이탈리아어, 불가리아어, 독일어, 그리스어로 경고 메시지와 함께 전문가 커뮤니케이션 지침에 따라 작성된 위기 사건의 영어 데이터 세트인 CrisiText를 이탈리아어, 불가리아어, 그리스어로 훈련시

Machine translation (Meta M2M100); the English original follows.

Abstract

Communicating with the public during an emergency entails issuing warning messages promptly. In Europe, it often requires producing them in more than one language. Recent work has shown that language models can be trained to generate warning messages as a crisis unfolds, but the available data covers only English. To fill this gap, we present CrisiLangs, a multilingual extension of CrisiText (an English dataset of crisis events paired with warning messages written according to expert communication guidelines) to Italian, Bulgarian, German, and Greek. Expert native speakers translated the warning messages of 1,000 events drawn from 411 scenarios, for a total of 5,000 event-message pairs across five languages. We test the resource to fine-tune a multilingual model on all five languages jointly, with and without the emergency guidelines in the prompt, and compare it with a zero-shot baseline. The fine-tuned models outperform the baseline on ROUGE-L, BLEU and BERTScore in every language and configuration. In a human preference study, low decoding temperatures receive the most preferences in all five languages and in both configurations, while the effect of the guidelines varies by language.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Resource (disambiguation), Warning system, Preference, Natural language processing, Language model

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31356, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange