Despite growing research on bias in large language models (LLMs), most work has focused on gender and race, with little attention to religious identity. This paper explores how religion is internally represented in LLMs and how it intersects with concepts of violence and geography. Using mechanistic interpretability and Sparse Autoencoders (SAEs) via the Neuronpedia API, we analyze latent feature activations across five models. We measure overlap between religion- and violence-related prompts and probe semantic patterns in activation contexts. While all five religions show comparable internal cohesion, Islam is more frequently linked to features associated with violent language. In contrast, geographic associations largely reflect real-world religious demographics, revealing how models embed both factual distributions and cultural stereotypes. These findings highlight the value of structural analysis in auditing not just outputs but also internal representations that shape model behavior.

Moldova has handed a note of protest to the Russian ambassador to Chisinau over alleged interference in its recent elections. The foreign ministry in Chisinau said in a statement on Tuesday that it turned over the "note of firm protest" in relation to the "illegal and deliberate interference" to envoy Oleg Ozerov during a meeting at its offices. Moldova has accused Russia of seeking to influence its recent presidential election and referendum on joining the European Union. Russia sought to affect results and delegitimise the democratic process, the ministry complained. Chisinau accused Russia of organising ineligible voting, bribery, and security threats in a bid to influence the votes.

This work introduces HistNERo, the first Romanian corpus for Named Entity Recognition (NER) in historical newspapers. The dataset contains 323k tokens of text, covering more than half of the 19th century (i.e., 1817) until the late part of the 20th century (i.e., 1990). Eight native Romanian speakers annotated the dataset with five named entities. The samples belong to one of the following four historical regions of Romania, namely Bessarabia, Moldavia, Transylvania, and Wallachia. We employed this proposed dataset to perform several experiments for NER using Romanian pre-trained language models. Our results show that the best model achieved a strict F1-score of 55.69%. Also, by reducing the discrepancies between regions through a novel domain adaption technique, we improved the performance on this corpus to a strict F1-score of 66.80%, representing an absolute gain of more than 10%.

This research delves into the intricate landscape of Musculoskeletal Disorder (MSD) risk factors, employing a novel fusion of Natural Language Processing (NLP) techniques and mode-based ranking methodologies. The primary objective is to advance the comprehension of MSD risk factors, their classification, and their relative severity, facilitating more targeted preventive and management interventions. The study utilizes eight diverse models, integrating pre-trained transformers, cosine similarity, and various distance metrics to classify risk factors into personal, biomechanical, workplace, psychological, and organizational classes. Key findings reveal that the BERT model with cosine similarity attains an overall accuracy of 28%, while the sentence transformer, coupled with Euclidean, Bray-Curtis, and Minkowski distances, achieves a flawless accuracy score of 100%. In tandem with the classification efforts, the research employs a mode-based ranking approach on survey data to discern the severity hierarchy of MSD risk factors. Intriguingly, the rankings align precisely with the previous literature, reaffirming the consistency and reliability of the approach. ``Working posture" emerges as the most severe risk factor, emphasizing the critical role of proper posture in preventing MSDs. The collective perceptions of survey participants underscore the significance of factors like "Job insecurity," "Effort reward imbalance," and "Poor employee facility" in contributing to MSD risks. The convergence of rankings provides actionable insights for organizations aiming to reduce the prevalence of MSDs. The study concludes with implications for targeted interventions, recommendations for improving workplace conditions, and avenues for future research.

The use of Deep Neural Network (DNN) models in risk-based decision-making has attracted extensive attention with broad applications in medical, finance, manufacturing, and quality control. To mitigate prediction-related risks in decision making, prediction confidence or uncertainty should be assessed alongside the overall performance of algorithms. Recent studies on Bayesian deep learning helps quantify prediction uncertainty arises from input noises and model parameters. However, the normality assumption of input noise in these models limits their applicability to problems involving categorical and discrete feature variables in tabular datasets. In this paper, we propose a mathematical framework to quantify prediction uncertainty for DNN models. The prediction uncertainty arises from errors in predictors that follow some known finite discrete distribution. We then conducted a case study using the framework to predict treatment outcome for tuberculosis patients during their course of treatment. The results demonstrate under a certain level of risk, we can identify risk-sensitive cases, which are prone to be misclassified due to error in predictors. Comparing to the Monte Carlo dropout method, our proposed framework is more aware of misclassification cases. Our proposed framework for uncertainty quantification in deep learning can support risk-based decision making in applications when discrete errors in predictors are present.

The DocRED dataset is one of the most popular and widely used benchmarks for document-level relation extraction (RE). It adopts a recommend-revise annotation scheme so as to have a large-scale annotated dataset. However, we find that the annotation of DocRED is incomplete, i.e., false negative samples are prevalent. We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset. To address the shortcoming, we re-annotate 4,053 documents in the DocRED dataset by adding the missed relation triples back to the original DocRED. We name our revised DocRED dataset Re-DocRED. We conduct extensive experiments with state-of-the-art neural models on both datasets, and the experimental results show that the models trained and evaluated on our Re-DocRED achieve performance improvements of around 13 F1 points. Moreover, we conduct a comprehensive analysis to identify the potential areas for further improvement. Our dataset is publicly available at https://github.com/tonytan48/Re-DocRED.

Littlestone and Warmuth [51] introduced sample compression schemes as an abstraction of the underlying structure of learning algorithms. Roughly, the aim of a sample compression scheme is to compress samples of a concept class (i.e., of a set system) C as much as possible, such that data coherent with the original samples can be reconstructed from the compressed data. There are two types of sample compression schemes: labeled, see [35, 51] and unlabeled, see [7, 34, 49]. A labeled compression scheme of size k compresses every sample of C to a labeled subsample of size at most k and an unlabeled compression scheme of size k compresses every sample of C to a subset of size at most k of the domain of the sample (see the end of the introduction for precise definitions). The Vapnik-Chervonenkis dimension (VC-dimension) of a set system, was introduced by [69] as a complexity measure of set systems. VC-dimension is central in PAC-learning and plays an important role in combinatorics, algorithmics, discrete geometry, and combinatorial optimization. In particular, it coincides with the rank in the theory of (complexes of) oriented matroids. Furthermore, within machine learning and closely tied to the topic of this paper, the sample compression conjecture of [35] and [51] states that any set system of VC-dimension d has a labeled sample compression scheme of size O(d). This question remains one of the oldest open problems in computational learning theory.

Romania's prime minister has presented his "new honorary adviser" – an artificial intelligence assistant named "Ion" that Nicolae Ciuca hailed as the first of its type. Developed by Romanian researchers, Ion's main task will be to scan social networks to inform the government "in real time of Romanians' proposals and wishes", Ciuca said on Wednesday. The liberal minister said the latest member of his entourage – a mirror-like structure with beeping interface – marked "an international first", describing Ion as "the first government adviser to use artificial intelligence". "Hi, you gave me life and my role is now to represent you, like a mirror," Ion's calm voice said at the launch. "What should I know about Romania?" Ion "will use technology and artificial intelligence to capture opinions in society" using "data publicly available on social networks", according to a government document detailing the project.

We introduce OpenEarthMap, a benchmark dataset, for global high-resolution land cover mapping. OpenEarthMap consists of 2.2 million segments of 5000 aerial and satellite images covering 97 regions from 44 countries across 6 continents, with manually annotated 8-class land cover labels at a 0.25--0.5m ground sampling distance. Semantic segmentation models trained on the OpenEarthMap generalize worldwide and can be used as off-the-shelf models in a variety of applications. We evaluate the performance of state-of-the-art methods for unsupervised domain adaptation and present challenging problem settings suitable for further technical development. We also investigate lightweight models using automated neural architecture search for limited computational resources and fast mapping. The dataset is available at https://open-earth-map.org.