Systems thinking provides us with a way to model the algorithmic fairness problem by allowing us to encode prior knowledge and assumptions about where we believe bias might exist in the data generating process. We can then model this using a series of causal graphs, enabling us to link AI/ML systems to politics and the law. By treating the fairness problem as a complex system, we can combine techniques from machine learning, causal inference, and system dynamics. Each of these analytical techniques is designed to capture different emergent aspects of fairness, allowing us to develop a deeper and more holistic view of the problem. This can help policymakers on both sides of the political aisle to understand the complex trade-offs that exist from different types of fairness policies, providing a blueprint for designing AI policy that is aligned to their political agendas.

Advanced Aerial Mobility encompasses many outstanding applications that promise to revolutionize modern logistics and pave the way for various public services and industry uses. However, throughout its history, the development of such systems has been impeded by the complexity of legal restrictions and physical constraints. While airspaces are often tightly shaped by various legal requirements, Unmanned Aerial Vehicles (UAV) must simultaneously consider, among others, energy demands, signal quality, and noise pollution. In this work, we address this challenge by presenting a novel architecture that integrates methods of Probabilistic Mission Design (ProMis) and Many-Objective Optimization for UAV routing. Hereby, our framework is able to comply with legal requirements under uncertainty while producing effective paths that minimize various physical costs a UAV needs to consider when traversing human-inhabited spaces. To this end, we combine hybrid probabilistic first-order logic for spatial reasoning with mixed deterministic-stochastic route optimization, incorporating physical objectives such as energy consumption and radio interference with a logical, probabilistic model of legal requirements. We demonstrate the versatility and advantages of our system in a large-scale empirical evaluation over real-world, crowd-sourced data from a map extract from the city of Paris, France, showing how a network of effective and compliant paths can be formed.

Social segregation in cities, spanning racial, residential, and income dimensions, is becoming more diverse and severe. As urban spaces and social relations grow more complex, residents in metropolitan areas experience varying levels of social segregation. If left unaddressed, this could lead to increased crime rates, heightened social tensions, and other serious issues. Effectively quantifying and analyzing the structures within urban spaces and resident interactions is crucial for addressing segregation. Previous studies have mainly focused on surface-level indicators of urban segregation, lacking comprehensive analyses of urban structure and mobility. This limitation fails to capture the full complexity of segregation. To address this gap, we propose a framework named Motif-Enhanced Graph Prototype Learning (MotifGPL),which consists of three key modules: prototype-based graph structure extraction, motif distribution discovery, and urban graph structure reconstruction. Specifically, we use graph structure prototype learning to extract key prototypes from both the urban spatial graph and the origin-destination graph, incorporating key urban attributes such as points of interest, street view images, and flow indices. To enhance interpretability, the motif distribution discovery module matches each prototype with similar motifs, representing simpler graph structures reflecting local patterns. Finally, we use the motif distribution results to guide the reconstruction of the two graphs. This model enables a detailed exploration of urban spatial structures and resident mobility patterns, helping identify and analyze motif patterns that influence urban segregation, guiding the reconstruction of urban graph structures. Experimental results demonstrate that MotifGPL effectively reveals the key motifs affecting urban social segregation and offer robust guidance for mitigating this issue.

Predictions in environments where a mix of legal policies, physical limitations, and operational preferences impacts an agent's motion are inherently difficult. Since Neuro-Symbolic systems allow for differentiable information flow between deep learning and symbolic building blocks, they present a promising avenue for expressing such high-level constraints. While prior work has demonstrated how to establish novel planning setups, e.g., in advanced aerial mobility tasks, their application in prediction tasks has been underdeveloped. We present the Constitutional Filter (CoFi), a novel filter architecture leveraging a Neuro-Symbolic representation of an agent's rules, i.e., its constitution, to (i) improve filter accuracy, (ii) leverage expert knowledge, (iii) incorporate deep learning architectures, and (iv) account for uncertainties in the environments through probabilistic spatial relations. CoFi follows a general, recursive Bayesian estimation setting, making it compatible with a vast landscape of estimation techniques such as Particle Filters. To underpin the advantages of CoFi, we validate its performance on real-world marine data from the Automatic Identification System and official Electronic Navigational Charts.

Social media firms could be ordered to use facial recognition technology to check children's ages. Millions of children could have their online profiles banned by the tech giants under plans to be set out by online regulator Ofcom next spring. Social media executives have been warned they could face huge fines and even prison sentences if they fail to follow guidance designed to ensure their users are not underage. John Higham, Ofcom's head of online safety policy, said platforms would be expected to remove children's accounts from their sites by using'highly accurate and effective' AI age checks. The regulator estimates that up to 60 per cent of eight to 11-year-olds have social media profiles, despite sites such as Facebook, Instagram, TikTok and Snapchat having minimum age limits of 13.

AI tools rapidly infiltrated peoples' lives in 2024, but AI lawmaking in the U.S. moved much more slowly. While dozens of AI-related bills were introduced this Congress--either to fund its research or mitigate its harms--most got stuck in partisan gridlock or buried under other priorities. In California, a bill aiming to hold AI companies liable for harms easily passed the state legislature, but was vetoed by Governor Gavin Newsom. This inaction has some AI skeptics increasingly worried. "We're seeing a replication of what we've seen in privacy and social media: of not setting up guardrails from the start to protect folks and drive real innovation," Ben Winters, the director of AI and data privacy at the Consumer Federation of America, tells TIME.

Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is often not the case for high-dimensional data, and it can be hard even for domain experts to mathematically specify which features are important. Can we instead automatically extract collections or groups of features that are aligned with expert knowledge? To address this gap, we present FIX (Features Interpretable to eXperts), a benchmark for measuring how well a collection of features aligns with expert knowledge. In collaboration with domain experts, we propose FIXScore, a unified expert alignment measure applicable to diverse real-world settings across cosmology, psychology, and medicine domains in vision, language, and time series data modalities. With FIXScore, we find that popular feature-based explanation methods have poor alignment with expert-specified knowledge, highlighting the need for new methods that can better identify features interpretable to experts.

The widespread adoption of machine learning in scientific research has created a fundamental tension between model opacity and scientific understanding. Whilst some advocate for intrinsically interpretable models, we introduce Computational Interpretabilism (CI) as a philosophical framework for post-hoc interpretability in scientific AI. Drawing parallels with human expertise, where post-hoc rationalisation coexists with reliable performance, CI establishes that scientific knowledge emerges through structured model interpretation when properly bounded by empirical validation. Through mediated understanding and bounded factivity, we demonstrate how post-hoc methods achieve epistemically justified insights without requiring complete mechanical transparency, resolving tensions between model complexity and scientific comprehension.

As LLMs are increasingly deployed in global applications, the importance of cultural sensitivity becomes paramount, ensuring that users from diverse backgrounds feel respected and understood. Cultural harm can arise when these models fail to align with specific cultural norms, resulting in misrepresentations or violations of cultural values. This work addresses the challenges of ensuring cultural sensitivity in LLMs, especially in small-parameter models that often lack the extensive training data needed to capture global cultural nuances. We present two key contributions: (1) A cultural harm test dataset, created to assess model outputs across different cultural contexts through scenarios that expose potential cultural insensitivities, and (2) A culturally aligned preference dataset, aimed at restoring cultural sensitivity through fine-tuning based on feedback from diverse annotators. These datasets facilitate the evaluation and enhancement of LLMs, ensuring their ethical and safe deployment across different cultural landscapes. Our results show that integrating culturally aligned feedback leads to a marked improvement in model behavior, significantly reducing the likelihood of generating culturally insensitive or harmful content. Ultimately, this work paves the way for more inclusive and respectful AI systems, fostering a future where LLMs can safely and ethically navigate the complexities of diverse cultural landscapes.

With the rapid advancement of Large Language Models (LLMs), significant safety concerns have emerged. Fundamentally, the safety of large language models is closely linked to the accuracy, comprehensiveness, and clarity of their understanding of safety knowledge, particularly in domains such as law, policy and ethics. This factuality ability is crucial in determining whether these models can be deployed and applied safely and compliantly within specific regions. To address these challenges and better evaluate the factuality ability of LLMs to answer short questions, we introduce the Chinese SafetyQA benchmark. Chinese SafetyQA has several properties (i.e., Chinese, Diverse, High-quality, Static, Easy-to-evaluate, Safety-related, Harmless). Based on Chinese SafetyQA, we perform a comprehensive evaluation on the factuality abilities of existing LLMs and analyze how these capabilities relate to LLM abilities, e.g., RAG ability and robustness against attacks.