If you are one of the few people on the planet who fancies a chat with Keir Starmer, then there's a new AI model for you. A former chief of staff to a Tory minister has created Nostrada, which aims to enable users to talk with an AI version of each of the UK parliament's 650 MPs – and lets you ask them anything you want. Founded by Leon Emirali, who worked for Steve Barclay, Nostrada gives users a chance to speak to the "digital twin", trained to replicate their political stances and mannerisms. It is intended for diplomats, lobbyists and members of the public, who can find out where each MP stands on each issue, as well as each of their colleagues. "Politicians provide such a rich data source because they can't stop talking," said Emirali.

Breakthroughs, discoveries, and DIY tips sent every weekday. If you recently received a voice message from an unusual number claiming to be your local congressperson, it's probably a scam. The FBI's crime division issued a warning this week about a new scheme in which bad actors use text messages and AI-generated voice clones to impersonate government officials. The scammers try to build a sense of connection with their target and eventually convince them to click on a malicious link that steals valuable login credentials. This scam is just the latest in a series of evolving attacks using convincing generative AI technology to trick people.

A couple of months ago, Vice-President J. D. Vance made an appearance in Washington at the American Dynamism summit, an annual event put on by the venture-capital firm Andreessen Horowitz. Members of Congress, startup founders, investors, and Defense Department officials sat in the audience. They gave Vance a standing ovation as he walked onstage, while Alabama's "Forty Hour Week (For a Livin')" played in the background. "You're here, I hope, because you love your country," Vance told the crowd. "You love its people, the opportunities that it's given you, and you recognize that building things--our capacity to create new innovation in the economy--cannot be a race to the bottom."

In the era of increasingly sophisticated natural language processing (NLP) systems, large language models (LLMs) have demonstrated remarkable potential for diverse applications, including tasks requiring nuanced textual understanding and contextual reasoning. This study investigates the capabilities of multiple state-of-the-art LLMs - GPT-3.5, GPT-4, LLAMA3, Mistral 7B, and Claude-2 - for zero-shot and few-shot annotation of a complex textual dataset comprising social media posts in Russian and Ukrainian. Specifically, the focus is on the binary classification task of identifying references to human rights violations within the dataset. To evaluate the effectiveness of these models, their annotations are compared against a gold standard set of human double-annotated labels across 1000 samples. The analysis includes assessing annotation performance under different prompting conditions, with prompts provided in both English and Russian. Additionally, the study explores the unique patterns of errors and disagreements exhibited by each model, offering insights into their strengths, limitations, and cross-linguistic adaptability. By juxtaposing LLM outputs with human annotations, this research contributes to understanding the reliability and applicability of LLMs for sensitive, domain-specific tasks in multilingual contexts. It also sheds light on how language models handle inherently subjective and context-dependent judgments, a critical consideration for their deployment in real-world scenarios.

Public procurement plays a critical role in government operations, ensuring the efficient allocation of resources and fostering economic growth. However, traditional procurement data is often stored in rigid, tabular formats, limiting its analytical potential and hindering transparency. This research presents a methodological framework for transforming structured procurement data into a semantic knowledge graph, leveraging ontological modeling and automated data transformation techniques. By integrating RDF and SPARQL-based querying, the system enhances the accessibility and interpretability of procurement records, enabling complex semantic queries and advanced analytics. Furthermore, by incorporating machine learning-driven predictive modeling, the system extends beyond conventional data analysis, offering insights into procurement trends and risk assessment. This work contributes to the broader field of public procurement intelligence by improving data transparency, supporting evidence-based decision-making, and enabling in-depth analysis of procurement activities in North Macedonia.

As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use. This is particularly critical in public health, where failure to retrieve relevant, accurate, and current information could significantly impact UK residents. However, currently little is known about LLM knowledge of UK Government public health information. To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries. To create PubHealthBench we extract free text from 687 current UK government guidance documents and implement an automated pipeline for generating MCQA samples. Assessing 24 LLMs on PubHealthBench we find the latest private LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use. However, in the free form setup we see lower performance with no model scoring >75%. Importantly we find in both setups LLMs have higher accuracy on guidance intended for the general public. Therefore, there are promising signs that state of the art (SOTA) LLMs are an increasingly accurate source of public health information, but additional safeguards or tools may still be needed when providing free form responses on public health topics.

Taiwanese China Studies (CS) has developed into a rich, interdisciplinary research field shaped by the unique geopolitical position and long standing academic engagement with Mainland China. This study responds to the growing need to systematically revisit and reorganize decades of Taiwan based CS scholarship by proposing an AI assisted approach that transforms unstructured academic texts into structured, interactive knowledge representations. We apply generative AI (GAI) techniques and large language models (LLMs) to extract and standardize entity relation triples from 1,367 peer reviewed CS articles published between 1996 and 2019. These triples are then visualized through a lightweight D3.js based system, forming the foundation of a domain specific knowledge graph and vector database for the field. This infrastructure allows users to explore conceptual nodes and semantic relationships across the corpus, revealing previously uncharted intellectual trajectories, thematic clusters, and research gaps. By decomposing textual content into graph structured knowledge units, our system enables a paradigm shift from linear text consumption to network based knowledge navigation. In doing so, it enhances scholarly access to CS literature while offering a scalable, data driven alternative to traditional ontology construction. This work not only demonstrates how generative AI can augment area studies and digital humanities but also highlights its potential to support a reimagined scholarly infrastructure for regional knowledge systems.

Enterprise networks are growing ever larger with a rapidly expanding attack surface, increasing the volume of security alerts generated from security controls. Security Operations Centre (SOC) analysts triage these alerts to identify malicious activity, but they struggle with alert fatigue due to the overwhelming number of benign alerts. Organisations are turning to managed SOC providers, where the problem is amplified by context switching and limited visibility into business processes. A novel system, named AACT, is introduced that automates SOC workflows by learning from analysts' triage actions on cybersecurity alerts. It accurately predicts triage decisions in real time, allowing benign alerts to be closed automatically and critical ones prioritised. This reduces the SOC queue allowing analysts to focus on the most severe, relevant or ambiguous threats. The system has been trained and evaluated on both real SOC data and an open dataset, obtaining high performance in identifying malicious alerts from benign alerts. Additionally, the system has demonstrated high accuracy in a real SOC environment, reducing alerts shown to analysts by 61% over six months, with a low false negative rate of 1.36% over millions of alerts.

This paper explores the application of Hamilton's rule to altruistic decision-making in multi-agent systems. Inspired by biological altruism, we introduce a framework that evaluates when individual agents should incur costs to benefit their neighbors. By adapting Hamilton's rule, we define agent ``fitness" in terms of task productivity rather than genetic survival. We formalize altruistic decision-making through a graph-based model of multi-agent interactions and propose a solution using collaborative control Lyapunov functions. The approach ensures that altruistic behaviors contribute to the collective goal-reaching efficiency of the system. We illustrate this framework on a multi-agent way-point navigation problem, where we show through simulation how agent importance levels influence altruistic decision-making, leading to improved coordination in navigation tasks.

Graph unlearning is a crucial approach for protecting user privacy by erasing the influence of user data on trained graph models. Recent developments in graph unlearning methods have primarily focused on maintaining model prediction performance while removing user information. However, we have observed that when user information is deleted from the model, the prediction distribution across different sensitive groups often changes. Furthermore, graph models are shown to be prone to amplifying biases, making the study of fairness in graph unlearning particularly important. This raises the question: Does graph unlearning actually introduce bias? Our findings indicate that the predictions of post-unlearning models become highly correlated with sensitive attributes, confirming the introduction of bias in the graph unlearning process. To address this issue, we propose a fair graph unlearning method, FGU. To guarantee privacy, FGU trains shard models on partitioned subgraphs, unlearns the requested data from the corresponding subgraphs, and retrains the shard models on the modified subgraphs. To ensure fairness, FGU employs a bi-level debiasing process: it first enables shard-level fairness by incorporating a fairness regularizer in the shard model retraining, and then achieves global-level fairness by aligning all shard models to minimize global disparity. Our experiments demonstrate that FGU achieves superior fairness while maintaining privacy and accuracy. Additionally, FGU is robust to diverse unlearning requests, ensuring fairness and utility performance across various data distributions.