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 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.

Despite the recent advances in Large Language Models, benchmarks for evaluating legal writing remain scarce due to the inherent complexity of assessing open-ended responses in this domain. One of the key challenges in evaluating language models on domain-specific tasks is finding test datasets that are public, frequently updated, and contain comprehensive evaluation guidelines. The Brazilian Bar Examination meets these requirements. We introduce oab-bench, a benchmark comprising 105 questions across seven areas of law from recent editions of the exam. The benchmark includes comprehensive evaluation guidelines and reference materials used by human examiners to ensure consistent grading. We evaluate the performance of four LLMs on oab-bench, finding that Claude-3.5 Sonnet achieves the best results with an average score of 7.93 out of 10, passing all 21 exams. We also investigated whether LLMs can serve as reliable automated judges for evaluating legal writing. Our experiments show that frontier models like OpenAI's o1 achieve a strong correlation with human scores when evaluating approved exams, suggesting their potential as reliable automated evaluators despite the inherently subjective nature of legal writing assessment. The source code and the benchmark -- containing questions, evaluation guidelines, model-generated responses, and their respective automated evaluations -- are publicly available.

Multilingual wordlists play a crucial role in comparative linguistics. While many studies have been carried out to test the power of computational methods for language subgrouping or divergence time estimation, few studies have put the data upon which these studies are based to a rigorous test. Here, we conduct a first experiment that tests the robustness of concept translation as an integral part of the compilation of multilingual wordlists. Investigating the variation in concept translations in independently compiled wordlists from 10 dataset pairs covering 9 different language families, we find that on average, only 83% of all translations yield the same word form, while identical forms in terms of phonetic transcriptions can only be found in 23% of all cases. Our findings can prove important when trying to assess the uncertainty of phylogenetic studies and the conclusions derived from them.

This work introduces a data-driven control approach for stabilizing high-dimensional dynamical systems from scarce data. The proposed context-aware controller inference approach is based on the observation that controllers need to act locally only on the unstable dynamics to stabilize systems. This means it is sufficient to learn the unstable dynamics alone, which are typically confined to much lower dimensional spaces than the high-dimensional state spaces of all system dynamics and thus few data samples are sufficient to identify them. Numerical experiments demonstrate that context-aware controller inference learns stabilizing controllers from orders of magnitude fewer data samples than traditional data-driven control techniques and variants of reinforcement learning. The experiments further show that the low data requirements of context-aware controller inference are especially beneficial in data-scarce engineering problems with complex physics, for which learning complete system dynamics is often intractable in terms of data and training costs.

Advances in image processing and analysis as well as machine learning techniques have contributed to the use of biometric recognition systems in daily people tasks. These tasks range from simple access to mobile devices to tagging friends in photos shared on social networks and complex financial operations on self-service devices for banking transactions. In China, the use of these systems goes beyond personal use becoming a country's government policy with the objective of monitoring the behavior of its population. On July 05th 2021, the Brazilian government announced acquisition of a biometric recognition system to be used nationwide. In the opposite direction to China, Europe and some American cities have already started the discussion about the legality of using biometric systems in public places, even banning this practice in their territory. In order to open a deeper discussion about the risks and legality of using these systems, this work exposes the vulnerabilities of biometric recognition systems, focusing its efforts on the face modality. Furthermore, it shows how it is possible to fool a biometric system through a well-known presentation attack approach in the literature called morphing. Finally, a list of ten concerns was created to start the discussion about the security of citizen data and data privacy law in the Age of Artificial Intelligence (AI).

Public Policies are not intrinsically positive or negative. Rather, policies provide varying levels of effects across different recipients. Methodologically, computational modeling enables the application of multiple influences on empirical data, thus allowing for heterogeneous response to policies. We use a random forest machine learning algorithm to emulate an agent-based model (ABM) and evaluate competing policies across 46 Metropolitan Regions (MRs) in Brazil. In doing so, we use input parameters and output indicators of 11,076 actual simulation runs and one million emulated runs. As a result, we obtain the optimal (and non-optimal) performance of each region over the policies. Optimum is defined as a combination of GDP production and the Gini coefficient inequality indicator for the full ensemble of Metropolitan Regions. Results suggest that MRs already have embedded structures that favor optimal or non-optimal results, but they also illustrate which policy is more beneficial to each place. In addition to providing MR-specific policies' results, the use of machine learning to simulate an ABM reduces the computational burden, whereas allowing for a much larger variation among model parameters. The coherence of results within the context of larger uncertainty--vis-\`a-vis those of the original ABM--reinforces robustness of the model. At the same time the exercise indicates which parameters should policymakers intervene on, in order to work towards precise policy optimal instruments.