Document simplification has recently attracted increasing attention due to its broader practical applicability compared to sentence-level simplification. Beyond simplifying individual sentences, this task involves preserving fluency, conciseness, and coherence across the entire text, often incorporating summarization techniques. Despite its importance, research in this area remains largely concentrated on a few languages, particularly English.In this work, we introduce LegalSim-PT, the first large-scale Portuguese dataset for document simplification based on legal texts. To mitigate reliance on manual evaluation, we combined data augmentation strategies with readability, semantic similarity, and diversity metrics to select the most suitable document pairs. We conducted a comprehensive analysis of the resulting dataset, first characterizing its surface features and comparing them with those of existing simplification corpora. Next, we assessed its quality using automatic metrics, linguistic indicators, and human evaluations. Finally, we select representative models as baselines and fine-tune two models on LegalSim-PT, achieving improved performance in document-level simplification.

While most essential medicines have become widely accessible across all social strata in Brazil due to government initiatives and market shifts, a significant barrier remains: the technical complexity of medication leaflets. This pragmatic and linguistic gap hinders patient comprehension of critical risks and benefits. Thus, adapting these texts into plain language patterns is crucial for patient safety and treatment adherence. Large language models have been increasingly effective as practical solutions for text simplification, an important Natural Language Processing (NLP) task that serves as a basis for several other linguistic and computational tasks. However, the scarcity of annotated datasets remains a bottleneck for rigorous evaluation. To bridge this gap, we propose a streamlined pipeline for generating simplified medical leaflets and introduce an initial benchmark dataset of 30 expertly annotated samples. Our results, supported by semantic and morphosyntactic evaluations, demonstrate that the proposed method produces high-quality, simplified content suitable for health applications.

Sentence simplification (SS) focuses on adapting sentences to enhance their readability and accessibility. While large language models (LLMs) match task-specific baselines in English SS, their performance in Portuguese remains underexplored. This paper presents a comprehensive performance comparison of 26 state-of-the-art LLMs in Portuguese SS, alongside two simplification models trained explicitly for this task and language. They are evaluated under a one-shot setting across scientific, news, and government datasets. We benchmark the models with our newly introduced Gov-Lang-BR corpus (1,703 complex-simple sentence pairs from Brazilian government agencies) and two established datasets: PorSimplesSent and Museum-PT. Our investigation takes advantage of both automatic metrics and large-scale linguistic analysis to examine the transformations achieved by the LLMs. Furthermore, a qualitative assessment of selected generated outputs provides deeper insights into simplification quality. Our findings reveal that while open-source LLMs have achieved impressive results, closed-source LLMs continue to outperform them in Portuguese SS.

Automatic text simplification focuses on transforming texts into a more comprehensible version without sacrificing their precision. However, automatic methods usually require (paired) datasets that can be rather scarce in languages other than English. This paper presents a new approach to automatic sentence simplification that leverages paraphrases, context, and linguistic attributes to overcome the absence of paired texts in Portuguese.We frame the simplification problem as a textual style transfer task and learn a style representation using the sentences around the target sentence in the document and its linguistic attributes. Moreover, unlike most unsupervised approaches that require style-labeled training data, we fine-tune strong pre-trained models using sentence-level paraphrases instead of annotated data. Our experiments show that our model achieves remarkable results, surpassing the current state-of-the-art (BART+ACCESS) while competitively matching a Large Language Model.