While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages, creating a critical barrier for others as simple translation fails to capture unique clinical and cultural nuances, such as endemic diseases. To address this, we introduce MedPT, the first large-scale, real-world corpus for Brazilian Portuguese, comprising 384,095 authentic question-answer pairs from patient-doctor interactions. The dataset underwent a meticulous multi-stage curation protocol, using a hybrid quantitative-qualitative analysis to filter noise and contextually enrich thousands of ambiguous queries. We further augmented the corpus via LLM-driven annotation, classifying questions into seven semantic types to capture user intent. Our analysis reveals its thematic breadth (3,200 topics) and unique linguistic properties, like the natural asymmetry in patient-doctor communication. To validate its utility, we benchmark a medical specialty routing task: fine-tuning a 1.7B parameter model achieves an outstanding 94\% F1-score on a 20-class setup. Furthermore, our qualitative error analysis shows misclassifications are not random but reflect genuine clinical ambiguities (e.g., between comorbid conditions), proving the dataset's deep semantic richness. We publicly release MedPT to foster the development of more equitable, accurate, and culturally-aware medical technologies for the Portuguese-speaking world.

Large Language Models (LLMs) excel on general-purpose NLP benchmarks, yet their capabilities in specialized domains remain underexplored. In e-commerce, existing evaluations-such as EcomInstruct, ChineseEcomQA, eCeLLM, and Shopping MMLU-suffer from limited task diversity (e.g., lacking product guidance and after-sales issues), limited task modalities (e.g., absence of multimodal data), synthetic or curated data, and a narrow focus on English and Chinese, leaving practitioners without reliable tools to assess models on complex, real-world shopping scenarios. We introduce EcomEval, a comprehensive multilingual and multimodal benchmark for evaluating LLMs in e-commerce. EcomEval covers six categories and 37 tasks (including 8 multimodal tasks), sourced primarily from authentic customer queries and transaction logs, reflecting the noisy and heterogeneous nature of real business interactions. To ensure both quality and scalability of reference answers, we adopt a semi-automatic pipeline in which large models draft candidate responses subsequently reviewed and modified by over 50 expert annotators with strong e-commerce and multilingual expertise. We define difficulty levels for each question and task category by averaging evaluation scores across models with different sizes and capabilities, enabling challenge-oriented and fine-grained assessment. EcomEval also spans seven languages-including five low-resource Southeast Asian languages-offering a multilingual perspective absent from prior work.

We introduce UniRST, the first unified RST-style discourse parser capable of handling 18 treebanks in 11 languages without modifying their relation inventories. To overcome inventory incompatibilities, we propose and evaluate two training strategies: Multi-Head, which assigns separate relation classification layer per inventory, and Masked-Union, which enables shared parameter training through selective label masking. We first benchmark monotreebank parsing with a simple yet effective augmentation technique for low-resource settings. We then train a unified model and show that (1) the parameter efficient Masked-Union approach is also the strongest, and (2) UniRST outperforms 16 of 18 mono-treebank baselines, demonstrating the advantages of a single-model, multilingual end-to-end discourse parsing across diverse resources.

This study presents the development of Geolog-IA, a novel conversational system based on artificial intelligence that responds naturally to questions about geology theses from the Central University of Ecuador. Our proposal uses the Llama 3.1 and Gemini 2.5 language models, which are complemented by a Retrieval Augmented Generation (RAG) architecture and an SQLite database. This strategy allows us to overcome problems such as hallucinations and outdated knowledge. The evaluation of Geolog-IA's performance with the BLEU metric reaches an average of 0.87, indicating high consistency and accuracy in the responses generated. The system offers an intuitive, web-based interface that facilitates interaction and information retrieval for directors, teachers, students, and administrative staff at the institution. This tool can be a key support in education, training, and research and establishes a basis for future applications in other disciplines.

This paper presents DeDisCo, Georgetown University's entry in the DISRPT 2025 shared task on discourse relation classification. We test two approaches, using an mt5-based encoder and a decoder based approach using the openly available Qwen model. We also experiment on training with augmented dataset for low-resource languages using matched data translated automatically from English, as well as using some additional linguistic features inspired by entries in previous editions of the Shared Task. Our system achieves a macro-accuracy score of 71.28, and we provide some interpretation and error analysis for our results.

We present our submission to Task 3 (Discourse Relation Classification) of the DISRPT 2025 shared task. Task 3 introduces a unified set of 17 discourse relation labels across 39 corpora in 16 languages and six discourse frameworks, posing significant multilingual and cross-formalism challenges. We first benchmark the task by fine-tuning multilingual BERT-based models (mBERT, XLM-RoBERTa-Base, and XLM-RoBERTa-Large) with two argument-ordering strategies and progressive unfreezing ratios to establish strong baselines. We then evaluate prompt-based large language models (namely Claude Opus 4.0) in zero-shot and few-shot settings to understand how LLMs respond to the newly proposed unified labels. Finally, we introduce HiDAC, a Hierarchical Dual-Adapter Contrastive learning model. Results show that while larger transformer models achieve higher accuracy, the improvements are modest, and that unfreezing the top 75% of encoder layers yields performance comparable to full fine-tuning while training far fewer parameters. Prompt-based models lag significantly behind fine-tuned transformers, and HiDAC achieves the highest overall accuracy (67.5%) while remaining more parameter-efficient than full fine-tuning.

Institute of Mathematics and Statistics, Federal University of Rio Grande do Sul (UFRGS), Av. Center for Coastal and Oceanic Geology Studies (CECO), Federal University of Rio Grande do Sul (UFRGS), Av. Abstract The forecast of wave variables are important for several applications that depend on a better description of the ocean state. Due to the chaotic behaviour of the differential equations which model this problem, a well know strategy to overcome the difficulties is basically to run several simulations, by for instance, varying the initial condition, and averaging the result of each of these, creating an ensemble. Moreover, in the last few years, considering the amount of available data and the computational power increase, machine learning algorithms have been applied as surrogate to traditional numerical models, yielding comparative or better results. In this work, we present a methodology to create an ensemble of different artificial neural networks architectures, namely, MLP, RNN, LSTM, CNN and a hybrid CNN-LSTM, which aims to predict significant wave height on six different locations in the Brazilian coast. The networks are trained using NOAA's numerical reforecast data and target the residual between observational data and the numerical model output. A new strategy to create the training and target datasets is demonstrated. Introduction Numerical simulations of both weather and ocean parameters rely on the evolution of nonlinear dynamical systems that have a high sensitivity on initial conditions. Considering that errors in the observations and analysis are present, and therefore in the initial conditions, the concept of a unique deterministic solution of the governing equations becomes fragile [1, 2].

This technical report analyzes the challenge of "hallucinations" (false information) in LLMs applied to law. It examines their causes, manifestations, and the effectiveness of the RAG mitigation strategy, highlighting its limitations and proposing holistic optimizations. The paper explores the ethical and regulatory implications, emphasizing human oversight as an irreplaceable role. It concludes that the solution lies not in incrementally improving generative models, but in adopting a "consultative" AI paradigm that prioritizes veracity and traceability, acting as a tool to amplify, not replace, professional judgment. -- Este informe técnico analiza el desafío de las "alucinaciones" (información falsa) en los LLMs aplicados al derecho. Se examinan sus causas, manifestaciones y la efectividad de la estrategia de mitigación RAG, exponiendo sus limitaciones y proponiendo optimizaciones holísticas. Se exploran las implicaciones éticas y regulatorias, enfatizando la supervisión humana como un rol insustituible. El documento concluye que la solución no reside en mejorar incrementalmente los modelos generativos, sino en adoptar un paradigma de IA "consultiva" que priorice la veracidad y la trazabilidad, actuando como una herramienta para amplificar, y no sustituir, el juicio profesional.

This systematic literature review analyzes the current state of compliance with Regulation (EU) 2024/1689 in autonomous robotic systems, focusing on cybersecurity frameworks and methodologies. Using the PRISMA protocol, 22 studies were selected from 243 initial records across IEEE Xplore, ACM DL, Scopus, and Web of Science. Findings reveal partial regulatory alignment: while progress has been made in risk management and encrypted communications, significant gaps persist in explainability modules, real-time human oversight, and knowledge base traceability. Only 40% of reviewed solutions explicitly address transparency requirements, and 30% implement failure intervention mechanisms. The study concludes that modular approaches integrating risk, supervision, and continuous auditing are essential to meet the AI Act mandates in autonomous robotics.

The automatic curation of discussion forums in online courses requires constant updates, making frequent retraining of Large Language Models (LLMs) a resource-intensive process. To circumvent the need for costly fine-tuning, this paper proposes and evaluates the use of Bayesian fusion. The approach combines the multidimensional classification scores of a pre-trained generic LLM with those of a classifier trained on local data. The performance comparison demonstrated that the proposed fusion improves the results compared to each classifier individually, and is competitive with the LLM fine-tuning approach