Saved in:
Bibliographic Details
Main Authors: García, Andrés Fernández, de la Rosa, Javier, Gonzalo, Julio, Morante, Roser, Amigó, Enrique, Benito-Santos, Alejandro, Carrillo-de-Albornoz, Jorge, Fresno, Víctor, Ghajari, Adrian, Marco, Guillermo, Plaza, Laura, Salido, Eva Sánchez
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.24908
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918150684016640
author García, Andrés Fernández
de la Rosa, Javier
Gonzalo, Julio
Morante, Roser
Amigó, Enrique
Benito-Santos, Alejandro
Carrillo-de-Albornoz, Jorge
Fresno, Víctor
Ghajari, Adrian
Marco, Guillermo
Plaza, Laura
Salido, Eva Sánchez
author_facet García, Andrés Fernández
de la Rosa, Javier
Gonzalo, Julio
Morante, Roser
Amigó, Enrique
Benito-Santos, Alejandro
Carrillo-de-Albornoz, Jorge
Fresno, Víctor
Ghajari, Adrian
Marco, Guillermo
Plaza, Laura
Salido, Eva Sánchez
contents The ability to summarize long documents succinctly is increasingly important in daily life due to information overload, yet there is a notable lack of such summaries for Spanish documents in general, and in the legal domain in particular. In this work, we present BOE-XSUM, a curated dataset comprising 3,648 concise, plain-language summaries of documents sourced from Spain's ``Bolet\'ın Oficial del Estado'' (BOE), the State Official Gazette. Each entry in the dataset includes a short summary, the original text, and its document type label. We evaluate the performance of medium-sized large language models (LLMs) fine-tuned on BOE-XSUM, comparing them to general-purpose generative models in a zero-shot setting. Results show that fine-tuned models significantly outperform their non-specialized counterparts. Notably, the best-performing model -- BERTIN GPT-J 6B (32-bit precision) -- achieves a 24\% performance gain over the top zero-shot model, DeepSeek-R1 (accuracies of 41.6\% vs.\ 33.5\%).
format Preprint
id arxiv_https___arxiv_org_abs_2509_24908
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BOE-XSUM: Extreme Summarization in Clear Language of Spanish Legal Decrees and Notifications
García, Andrés Fernández
de la Rosa, Javier
Gonzalo, Julio
Morante, Roser
Amigó, Enrique
Benito-Santos, Alejandro
Carrillo-de-Albornoz, Jorge
Fresno, Víctor
Ghajari, Adrian
Marco, Guillermo
Plaza, Laura
Salido, Eva Sánchez
Computation and Language
The ability to summarize long documents succinctly is increasingly important in daily life due to information overload, yet there is a notable lack of such summaries for Spanish documents in general, and in the legal domain in particular. In this work, we present BOE-XSUM, a curated dataset comprising 3,648 concise, plain-language summaries of documents sourced from Spain's ``Bolet\'ın Oficial del Estado'' (BOE), the State Official Gazette. Each entry in the dataset includes a short summary, the original text, and its document type label. We evaluate the performance of medium-sized large language models (LLMs) fine-tuned on BOE-XSUM, comparing them to general-purpose generative models in a zero-shot setting. Results show that fine-tuned models significantly outperform their non-specialized counterparts. Notably, the best-performing model -- BERTIN GPT-J 6B (32-bit precision) -- achieves a 24\% performance gain over the top zero-shot model, DeepSeek-R1 (accuracies of 41.6\% vs.\ 33.5\%).
title BOE-XSUM: Extreme Summarization in Clear Language of Spanish Legal Decrees and Notifications
topic Computation and Language
url https://arxiv.org/abs/2509.24908