Three aid workers killed, 4 wounded in RSF drone attack in Sudan's Kordofan At least three aid workers have been killed and four others wounded in a drone attack by the paramilitary Rapid Support Forces (RSF) on an aid convoy in Sudan's South Kordofan state, according to the Sudan Doctors Network, in the latest carnage against civilians caught up in the nation's brutal civil war. The convoy of trucks carrying food and humanitarian supplies was targeted by the RSF, and its ally, the Sudan People's Liberation Movement-North, while travelling through the Kartala area on its way to the cities of Kadugli and Dilling on Thursday. The network said that this attack marked the "second such incident in less than a month, following the shelling of a United Nations aid convoy in the town of Al-Rahad," adding: "this dangerous escalation threatens the safety of humanitarian operations and further exacerbates civilian suffering". The Sudan Doctors Network reiterated its call to the "international community, the United Nations, and human rights organisations to exert urgent and effective pressure on the leadership of the Rapid Support Forces to ensure the protection of aid convoys and their workers, to open safe and sustainable humanitarian corridors, and to hold those responsible for targeting aid accountable". Al Jazeera could not independently verify the latest RSF attack, which came a month after the government-aligned Sudanese Armed Forces (SAF) announced that it had broken a nearly two-year-long RSF siege on Dilling.

Artificial intelligence risks increasing inequality between developed and developing countries, a United Nations report has warned. The report, titled "The Next Great Divergence" and released by the United Nations Development Programme's Asia and Pacific regional bureau on Tuesday, calls for urgent, coordinated policy action to manage the impact of the technology. "We think that AI is heralding a new era of rising inequality between countries, following years of convergence in the last 50 years," Philip Schellekens, the bureau's chief economist, told a briefing in Geneva, according to the Reuters news agency. The report argues that AI, like the Industrial Revolution before it, has the potential to unlock unprecedented opportunities or deepen existing divides, across a global landscape marked by vast gaps in wealth, skills, and digital access. Even wealthier countries would suffer if poorer states were left behind by the AI revolution, said Schellekens. "If inequality continues to rise, the spillover effects of that in terms of the security agenda, in terms of undocumented forms of migration, will also become more daunting," he worries.

The quality and accessibility of multilingual datasets are crucial for advancing machine translation. However, previous corpora built from United Nations documents have suffered from issues such as opaque process, difficulty of reproduction, and limited scale. To address these challenges, we introduce a complete end-to-end solution, from data acquisition via web scraping to text alignment. The entire process is fully reproducible, with a minimalist single-machine example and optional distributed computing steps for scalability. At its core, we propose a new Graph-Aided Paragraph Alignment (GAPA) algorithm for efficient and flexible paragraph-level alignment. The resulting corpus contains over 713 million English tokens, more than doubling the scale of prior work. To the best of our knowledge, this represents the largest publicly available parallel corpus composed entirely of human-translated, non-AI-generated content. Our code and corpus are accessible under the MIT License.

Religion and spirituality (R/S) are complex and highly domain-dependent concepts which have long confounded researchers and policymakers. Due to their context-specificity, R/S are difficult to operationalize in conventional archival search strategies, particularly when datasets are very large, poorly accessible, and marked by information noise. As a result, considerable time investments and specialist knowledge is often needed to extract actionable insights related to R/S from general archival sources, increasing reliance on published literature and manual desk reviews. To address this challenge, we present SpiritRAG, an interactive Question Answering (Q&A) system based on Retrieval-Augmented Generation (RAG). Built using 7,500 United Nations (UN) resolution documents related to R/S in the domains of health and education, SpiritRAG allows researchers and policymakers to conduct complex, context-sensitive database searches of very large datasets using an easily accessible, chat-based web interface. SpiritRAG is lightweight to deploy and leverages both UN documents and user provided documents as source material. A pilot test and evaluation with domain experts on 100 manually composed questions demonstrates the practical value and usefulness of SpiritRAG.

Analyzing large volumes of case law to uncover evolving legal principles, across multiple cases, on a given topic is a demanding task for legal professionals. Structured topical reports provide an effective solution by summarizing key issues, principles, and judgments, enabling comprehensive legal analysis on a particular topic. While prior works have advanced query-based individual case summarization, none have extended to automatically generating multi-case structured reports. To address this, we introduce LexGenie, an automated LLM-based pipeline designed to create structured reports using the entire body of case law on user-specified topics within the European Court of Human Rights jurisdiction. LexGenie retrieves, clusters, and organizes relevant passages by topic to generate a structured outline and cohesive content for each section. Expert evaluation confirms LexGenie's utility in producing structured reports that enhance efficient, scalable legal analysis.

Large Language Models (LLMs) have achieved significant advances in natural language processing, yet their potential for high-stake political decision-making remains largely unexplored. This paper addresses the gap by focusing on the application of LLMs to the United Nations (UN) decision-making process, where the stakes are particularly high and political decisions can have far-reaching consequences. We introduce a novel dataset comprising publicly available UN Security Council (UNSC) records from 1994 to 2024, including draft resolutions, voting records, and diplomatic speeches. Using this dataset, we propose the United Nations Benchmark (UNBench), the first comprehensive benchmark designed to evaluate LLMs across four interconnected political science tasks: co-penholder judgment, representative voting simulation, draft adoption prediction, and representative statement generation. These tasks span the three stages of the UN decision-making process--drafting, voting, and discussing--and aim to assess LLMs' ability to understand and simulate political dynamics. Our experimental analysis demonstrates the potential and challenges of applying LLMs in this domain, providing insights into their strengths and limitations in political science. This work contributes to the growing intersection of AI and political science, opening new avenues for research and practical applications in global governance. The UNBench Repository can be accessed at: https://github.com/yueqingliang1/UNBench.

Prior case retrieval (PCR) is crucial for legal practitioners to find relevant precedent cases given the facts of a query case. Existing approaches often overlook the underlying semantic intent in determining relevance with respect to the query case. In this work, we propose LeCoPCR, a novel approach that explicitly generate intents in the form of legal concepts from a given query case facts and then augments the query with these concepts to enhance models understanding of semantic intent that dictates relavance. To overcome the unavailability of annotated legal concepts, we employ a weak supervision approach to extract key legal concepts from the reasoning section using Determinantal Point Process (DPP) to balance quality and diversity. Experimental results on the ECtHR-PCR dataset demonstrate the effectiveness of leveraging legal concepts and DPP-based key concept extraction.

The number of people living in urban areas has tripled in the last 50 years, meaning when a major natural disaster such as an earthquake strikes a city, more lives are in danger. Meanwhile, the strength and frequency of extreme weather events has increased--a trend set to continue as the climate warms. That is spurring efforts around the world to develop a new generation of earthquake monitoring and climate forecasting systems to make detecting and responding to disasters quicker, cheaper, and more accurate than ever. On Nov. 6, at the Barcelona Supercomputing Center in Spain, the Global Initiative on Resilience to Natural Hazards through AI Solutions will meet for the first time. The new United Nations initiative aims to guide governments, organizations, and communities in using AI for disaster management.

Inspired by the legal doctrine of stare decisis, which leverages precedents (prior cases) for informed decision-making, we explore methods to integrate them into LJP models. To facilitate precedent retrieval, we train a retriever with a fine-grained relevance signal based on the overlap ratio of alleged articles between cases. We investigate two strategies to integrate precedents: direct incorporation at inference via label interpolation based on case proximity and during training via a precedent fusion module using a stacked-cross attention model. We employ joint training of the retriever and LJP models to address latent space divergence between them. Our experiments on LJP tasks from the ECHR jurisdiction reveal that integrating precedents during training coupled with joint training of the retriever and LJP model, outperforms models without precedents or with precedents incorporated only at inference, particularly benefiting sparser articles.

In high-stakes decision-making tasks within legal NLP, such as Case Outcome Classification (COC), quantifying a model's predictive confidence is crucial. Confidence estimation enables humans to make more informed decisions, particularly when the model's certainty is low, or where the consequences of a mistake are significant. However, most existing COC works prioritize high task performance over model reliability. This paper conducts an empirical investigation into how various design choices including pre-training corpus, confidence estimator and fine-tuning loss affect the reliability of COC models within the framework of selective prediction. Our experiments on the multi-label COC task, focusing on European Court of Human Rights (ECtHR) cases, highlight the importance of a diverse yet domain-specific pre-training corpus for better calibration. Additionally, we demonstrate that larger models tend to exhibit overconfidence, Monte Carlo dropout methods produce reliable confidence estimates, and confident error regularization effectively mitigates overconfidence. To our knowledge, this is the first systematic exploration of selective prediction in legal NLP. Our findings underscore the need for further research on enhancing confidence measurement and improving the trustworthiness of models in the legal domain.