Marta Villegas

Daniel Tamayo, Iñaki Lacunza, Paula Rivera-Hidalgo et al.

We introduce MrBERT, a family of 150M-300M parameter encoders built on the ModernBERT architecture and pre-trained on 35 languages and code. Through targeted adaptation, this model family achieves state-of-the-art results on Catalan- and Spanish-specific tasks, while establishing robust performance across specialized biomedical and legal domains. To bridge the gap between research and production, we incorporate Matryoshka Representation Learning (MRL), enabling flexible vector sizing that significantly reduces inference and storage costs. Ultimately, the MrBERT family demonstrates that modern encoder architectures can be optimized for both localized linguistic excellence and efficient, high-stakes domain specialization. We open source the complete model family on Huggingface.

Iñaki Lacunza, José Javier Saiz, Alexander Shvets et al.

Current large language models (LLMs) are trained on massive amounts of text data, primarily from a few dominant languages. Studies suggest that this over-reliance on high-resource languages, such as English, hampers LLM performance in mid- and low-resource languages. To mitigate this problem, we propose to (i) optimize the language distribution by training a small proxy model within a domain-reweighing DoGE algorithm that we extend to XDoGE for a multilingual setup, and (ii) rescale the data and train a full-size model with the established language weights either from scratch or within a continual pre-training phase (CPT). We target six languages possessing a variety of geographic and intra- and inter-language-family relations, namely, English and Spanish (high-resource), Portuguese and Catalan (mid-resource), Galician and Basque (low-resource). We experiment with Salamandra-2b, which is a promising model for these languages. We investigate the effects of substantial data repetition on minor languages and under-sampling on dominant languages using the IberoBench framework for quantitative evaluation. Finally, we release a new promising IberianLLM-7B-Instruct model centering on Iberian languages and English that we pretrained from scratch and further improved using CPT with the XDoGE weights.

Daniel Tamayo, Aitor Gonzalez-Agirre, Javier Hernando et al.

Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing knowledge editing methods across languages and delving into the role of attention mechanisms in this process. Drawing from the insights gained, we propose Mass-Editing Memory with Attention in Transformers (MEMAT), a method that achieves significant improvements in all metrics while requiring minimal parameter modifications. MEMAT delivers a remarkable 10% increase in magnitude metrics, benefits languages not included in the training data and also demonstrates a high degree of portability. Our code and data are at https://github.com/dtamayo-nlp/MEMAT.

Aitor Gonzalez-Agirre, Marc Pàmies, Joan Llop et al.

This work introduces Salamandra, a suite of open-source decoder-only large language models available in three different sizes: 2, 7, and 40 billion parameters. The models were trained from scratch on highly multilingual data that comprises text in 35 European languages and code. Our carefully curated corpus is made exclusively from open-access data compiled from a wide variety of sources. Along with the base models, supplementary checkpoints that were fine-tuned on public-domain instruction data are also released for chat applications. Additionally, we also share our preliminary experiments on multimodality, which serve as proof-of-concept to showcase potential applications for the Salamandra family. Our extensive evaluations on multilingual benchmarks reveal that Salamandra has strong capabilities, achieving competitive performance when compared to similarly sized open-source models. We provide comprehensive evaluation results both on standard downstream tasks as well as key aspects related to bias and safety.With this technical report, we intend to promote open science by sharing all the details behind our design choices, data curation strategy and evaluation methodology. In addition to that, we deviate from the usual practice by making our training and evaluation scripts publicly accessible. We release all models under a permissive Apache 2.0 license in order to foster future research and facilitate commercial use, thereby contributing to the open-source ecosystem of large language models.

Casimiro Pio Carrino, Jordi Armengol-Estapé, Asier Gutiérrez-Fandiño et al.

This work presents biomedical and clinical language models for Spanish by experimenting with different pretraining choices, such as masking at word and subword level, varying the vocabulary size and testing with domain data, looking for better language representations. Interestingly, in the absence of enough clinical data to train a model from scratch, we applied mixed-domain pretraining and cross-domain transfer approaches to generate a performant bio-clinical model suitable for real-world clinical data. We evaluated our models on Named Entity Recognition (NER) tasks for biomedical documents and challenging hospital discharge reports. When compared against the competitive mBERT and BETO models, we outperform them in all NER tasks by a significant margin. Finally, we studied the impact of the model's vocabulary on the NER performances by offering an interesting vocabulary-centric analysis. The results confirm that domain-specific pretraining is fundamental to achieving higher performances in downstream NER tasks, even within a mid-resource scenario. To the best of our knowledge, we provide the first biomedical and clinical transformer-based pretrained language models for Spanish, intending to boost native Spanish NLP applications in biomedicine. Our best models are freely available in the HuggingFace hub: https://huggingface.co/BSC-TeMU.

Iñigo Pikabea, Iñaki Lacunza, Oriol Pareras et al.

Rapid advancements in Visual Language Models (VLMs) have transformed multimodal understanding but are often constrained by generating English responses regardless of the input language. This phenomenon has been termed as Image-induced Fidelity Loss (IFL) and stems from limited multimodal multilingual training data. To address this, we propose a continuous multilingual integration strategy that injects text-only multilingual data during visual instruction tuning, preserving the language model's original multilingual capabilities. Extensive evaluations demonstrate that our approach significantly improves linguistic fidelity across languages without degradation in visual performance. We also explore model merging, which improves language fidelity but comes at the cost of visual performance. In contrast, our core method achieves robust multilingual alignment without trade-offs, offering a scalable and effective path to mitigating IFL for global VLM adoption.

Iñaki Lacunza, Javier Garcia Gilabert, Francesca De Luca Fornaciari et al.

We present ACADATA, a high-quality parallel dataset for academic translation, that consists of two subsets: ACAD-TRAIN, which contains approximately 1.5 million author-generated paragraph pairs across 96 language directions and ACAD-BENCH, a curated evaluation set of almost 6,000 translations covering 12 directions. To validate its utility, we fine-tune two Large Language Models (LLMs) on ACAD-TRAIN and benchmark them on ACAD-BENCH against specialized machine-translation systems, general-purpose, open-weight LLMs, and several large-scale proprietary models. Experimental results demonstrate that fine-tuning on ACAD-TRAIN leads to improvements in academic translation quality by +6.1 and +12.4 d-BLEU points on average for 7B and 2B models respectively, while also improving long-context translation in a general domain by up to 24.9% when translating out of English. The fine-tuned top-performing model surpasses the best propietary and open-weight models on academic translation domain. By releasing ACAD-TRAIN, ACAD-BENCH and the fine-tuned models, we provide the community with a valuable resource to advance research in academic domain and long-context translation.

Carlos Rodriguez-Penagos, Carme Armentano-Oller, Marta Villegas et al.

The Catalan Language Understanding Benchmark (CLUB) encompasses various datasets representative of different NLU tasks that enable accurate evaluations of language models, following the General Language Understanding Evaluation (GLUE) example. It is part of AINA and PlanTL, two public funding initiatives to empower the Catalan language in the Artificial Intelligence era.

Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Aitor Gonzalez-Agirre et al.

There are many Language Models for the English language according to its worldwide relevance. However, for the Spanish language, even if it is a widely spoken language, there are very few Spanish Language Models which result to be small and too general. Legal slang could be think of a Spanish variant on its own as it is very complicated in vocabulary, semantics and phrase understanding. For this work we gathered legal-domain corpora from different sources, generated a model and evaluated against Spanish general domain tasks. The model provides reasonable results in those tasks.

Casimiro Pio Carrino, Jordi Armengol-Estapé, Ona de Gibert Bonet et al.

We introduce CoWeSe (the Corpus Web Salud Español), the largest Spanish biomedical corpus to date, consisting of 4.5GB (about 750M tokens) of clean plain text. CoWeSe is the result of a massive crawler on 3000 Spanish domains executed in 2020. The corpus is openly available and already preprocessed. CoWeSe is an important resource for biomedical and health NLP in Spanish and has already been employed to train domain-specific language models and to produce word embbedings. We released the CoWeSe corpus under a Creative Commons Attribution 4.0 International license, both in Zenodo (\url{https://zenodo.org/record/4561971\#.YTI5SnVKiEA}).

Jordi Armengol-Estapé, Casimiro Pio Carrino, Carlos Rodriguez-Penagos et al.

Multilingual language models have been a crucial breakthrough as they considerably reduce the need of data for under-resourced languages. Nevertheless, the superiority of language-specific models has already been proven for languages having access to large amounts of data. In this work, we focus on Catalan with the aim to explore to what extent a medium-sized monolingual language model is competitive with state-of-the-art large multilingual models. For this, we: (1) build a clean, high-quality textual Catalan corpus (CaText), the largest to date (but only a fraction of the usual size of the previous work in monolingual language models), (2) train a Transformer-based language model for Catalan (BERTa), and (3) devise a thorough evaluation in a diversity of settings, comprising a complete array of downstream tasks, namely, Part of Speech Tagging, Named Entity Recognition and Classification, Text Classification, Question Answering, and Semantic Textual Similarity, with most of the corresponding datasets being created ex novo. The result is a new benchmark, the Catalan Language Understanding Benchmark (CLUB), which we publish as an open resource, together with the clean textual corpus, the language model, and the cleaning pipeline. Using state-of-the-art multilingual models and a monolingual model trained only on Wikipedia as baselines, we consistently observe the superiority of our model across tasks and settings.

Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Marc Pàmies et al.

This work presents MarIA, a family of Spanish language models and associated resources made available to the industry and the research community. Currently, MarIA includes RoBERTa-base, RoBERTa-large, GPT2 and GPT2-large Spanish language models, which can arguably be presented as the largest and most proficient language models in Spanish. The models were pretrained using a massive corpus of 570GB of clean and deduplicated texts with 135 billion words extracted from the Spanish Web Archive crawled by the National Library of Spain between 2009 and 2019. We assessed the performance of the models with nine existing evaluation datasets and with a novel extractive Question Answering dataset created ex novo. Overall, MarIA models outperform the existing Spanish models across a variety of NLU tasks and training settings.

Anastasios Nentidis, Anastasia Krithara, Konstantinos Bougiatiotis et al.

In this paper, we present an overview of the eighth edition of the BioASQ challenge, which ran as a lab in the Conference and Labs of the Evaluation Forum (CLEF) 2020. BioASQ is a series of challenges aiming at the promotion of systems and methodologies for large-scale biomedical semantic indexing and question answering. To this end, shared tasks are organized yearly since 2012, where different teams develop systems that compete on the same demanding benchmark datasets that represent the real information needs of experts in the biomedical domain. This year, the challenge has been extended with the introduction of a new task on medical semantic indexing in Spanish. In total, 34 teams with more than 100 systems participated in the three tasks of the challenge. As in previous years, the results of the evaluation reveal that the top-performing systems managed to outperform the strong baselines, which suggests that state-of-the-art systems keep pushing the frontier of research through continuous improvements.

Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé et al.

The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic properties of the model to determine whether it is learning appropriately. In this work, we suggest studying the training of neural networks with Algebraic Topology, specifically Persistent Homology (PH). Using simplicial complex representations of neural networks, we study the PH diagram distance evolution on the neural network learning process with different architectures and several datasets. Results show that the PH diagram distance between consecutive neural network states correlates with the validation accuracy, implying that the generalization error of a neural network could be intrinsically estimated without any holdout set.

Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Casimiro Pio Carrino et al.

We computed both Word and Sub-word Embeddings using FastText. For Sub-word embeddings we selected Byte Pair Encoding (BPE) algorithm to represent the sub-words. We evaluated the Biomedical Word Embeddings obtaining better results than previous versions showing the implication that with more data, we obtain better representations.

David Pérez-Fernández, Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé et al.

Characterizing the structural properties of neural networks is crucial yet poorly understood, and there are no well-established similarity measures between networks. In this work, we observe that neural networks can be represented as abstract simplicial complex and analyzed using their topological 'fingerprints' via Persistent Homology (PH). We then describe a PH-based representation proposed for characterizing and measuring similarity of neural networks. We empirically show the effectiveness of this representation as a descriptor of different architectures in several datasets. This approach based on Topological Data Analysis is a step towards better understanding neural networks and serves as a useful similarity measure.

Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Marta Villegas

Researchers that work for the same institution use their email as the main communication tool. Email can be one of the most fruitful attack vectors of research institutions as they also contain access to all accounts and thus to all private information. We propose an approach for analyzing in terms of security research institutions' communication networks. We first obtained institutions' communication networks as well as a method to analyze possible breaches of collected emails. We downloaded the network of 4 different research centers, three from Spain and one from Portugal. We then ran simulations of Susceptible-Exposed-Infected-Recovered (SEIR) complex network dynamics model for analyzing the vulnerability of the network. More than half of the nodes have more than one security breach, and our simulation results show that more than 90\% of the networks' nodes are vulnerable. This method can be employed for enhancing security of research centers and can make email accounts' use security-aware. It may additionally open new research lines in communication security. Finally, we manifest that, due to confidentiality reasons, the sources we utilized for obtaining communication networks should not be providing the information that we were able to gather.