Large Language Models for the Summarization of Czech Documents: From History to the Present

TL;DR

The paper addresses the underexplored area of Czech text summarization, with a focus on historical Czech, by evaluating multilingual large language models (Mistral 7B and mT5) and a translation-based Translation-Summarization-Translation (TST) pipeline. It introduces Posel od Čerchova, a historical Czech corpus designed to benchmark abstractive summarization in diachronic contexts, alongside baselines on the modern Czech SumeCzech dataset. Experimental results show that Mistral-based models (M7B-SC) achieve state-of-the-art performance on SumeCzech, with mT5-SC as a strong competitor, while the TST approach offers a viable alternative in some scenarios. The work lays foundational resources and baselines for Czech historical document processing, enabling broader research in low-resource and historical summarization within digital humanities.

Abstract

Text summarization is the task of automatically condensing longer texts into shorter, coherent summaries while preserving the original meaning and key information. Although this task has been extensively studied in English and other high-resource languages, Czech summarization, particularly in the context of historical documents, remains underexplored. This is largely due to the inherent linguistic complexity of Czech and the lack of high-quality annotated datasets. In this work, we address this gap by leveraging the capabilities of Large Language Models (LLMs), specifically Mistral and mT5, which have demonstrated strong performance across a wide range of natural language processing tasks and multilingual settings. In addition, we also propose a translation-based approach that first translates Czech texts into English, summarizes them using an English-language model, and then translates the summaries back into Czech. Our study makes the following main contributions: We demonstrate that LLMs achieve new state-of-the-art results on the SumeCzech dataset, a benchmark for modern Czech text summarization, showing the effectiveness of multilingual LLMs even for morphologically rich, medium-resource languages like Czech. We introduce a new dataset, Posel od Čerchova, designed for the summarization of historical Czech texts. This dataset is derived from digitized 19th-century publications and annotated for abstractive summarization. We provide initial baselines using modern LLMs to facilitate further research in this underrepresented area. By combining cutting-edge models with both modern and historical Czech datasets, our work lays the foundation for further progress in Czech summarization and contributes valuable resources for future research in Czech historical document processing and low-resource summarization more broadly.