AraFinNews: Arabic Financial Summarisation with Domain-Adapted LLMs

TL;DR

AraFinNews is a large Arabic financial news dataset that enables evaluation of domain-specific language models, demonstrating that domain adaptation improves summarisation quality, especially for quantitative and entity-related information.

Contribution

The paper introduces AraFinNews, the largest Arabic financial news dataset, and evaluates the impact of domain-adapted LLMs on financial text summarisation.

Findings

Domain-adapted models produce more coherent summaries.

Financial domain pretraining improves numerical and entity handling.

The dataset facilitates benchmarking Arabic financial NLP tasks.

Abstract

We introduce AraFinNews, the largest publicly available Arabic financial news dataset to date, comprising 212,500 article-headline pairs spanning a decade of reporting from 2015 to 2025. Designed as an Arabic counterpart to major English summarisation corpora such as CNN/DailyMail, AraFinNews provides a realistic benchmark for evaluating domain-specific language understanding and generation in financial contexts. Using this resource, we investigate the impact of domain specificity on abstractive summarisation of Arabic financial texts with large language models (LLMs). In particular, we evaluate transformer-based models: mT5, AraT5, and the domain-adapted FinAraT5 to examine how financial-domain pretraining influences accuracy, numerical reliability, and stylistic alignment with professional reporting. Experimental results show that domain-adapted models generate more coherent summaries, especially in their handling of quantitative and entity-centric information. These findings highlight the importance of domain-specific adaptation for improving narrative fluency in Arabic financial summarisation. The dataset is freely available for non-commercial research at https://github.com/ArabicNLP-uk/AraFinNews.