CrossNews-UA: A Cross-lingual News Semantic Similarity Benchmark for Ukrainian, Polish, Russian, and English
This work addresses the need for scalable datasets to detect fake news across multiple languages, particularly for Ukrainian and related languages, but it is incremental as it builds on existing cross-lingual news analysis efforts.
The authors tackled the problem of cross-lingual news analysis by introducing a scalable crowdsourcing pipeline to create a new dataset, CrossNews-UA, for semantic similarity assessment across Ukrainian, Polish, Russian, and English, and tested various models to highlight challenges in this task.
In the era of social networks and rapid misinformation spread, news analysis remains a critical task. Detecting fake news across multiple languages, particularly beyond English, poses significant challenges. Cross-lingual news comparison offers a promising approach to verify information by leveraging external sources in different languages (Chen and Shu, 2024). However, existing datasets for cross-lingual news analysis (Chen et al., 2022a) were manually curated by journalists and experts, limiting their scalability and adaptability to new languages. In this work, we address this gap by introducing a scalable, explainable crowdsourcing pipeline for cross-lingual news similarity assessment. Using this pipeline, we collected a novel dataset CrossNews-UA of news pairs in Ukrainian as a central language with linguistically and contextually relevant languages-Polish, Russian, and English. Each news pair is annotated for semantic similarity with detailed justifications based on the 4W criteria (Who, What, Where, When). We further tested a range of models, from traditional bag-of-words, Transformer-based architectures to large language models (LLMs). Our results highlight the challenges in multilingual news analysis and offer insights into models performance.