arXiv subjects

Sennay Ghebreab

Publications and source records attributed to Sennay Ghebreab.

15 recordsLinked to original sources

arXiv2026

From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch

Large language models are increasingly being deployed in governmental settings, yet few existing evaluation frameworks jointly reflect the values of public administration and the linguistic requirements of non-English contexts. We present the "Grip on LLMs" framework, a systematic evaluation suite for Dutch governmental use developed in collaboration with domain experts from a major Dutch municipal organisation. Through an advisory board process, user research, and a survey of the users of a civil-servant chatbot, we identify six evaluation dimensions (factuality, honesty, social bias, energy consumption, cost, and training data transparency) and operationalise them into a benchmark suite covering more than 30 multilingual and Dutch-specific models. Our results reveal that no single model excels across all dimensions, and that trade-offs are unavoidable: higher quality consistently comes at greater environmental impact and financial cost, while bias remains largely independent of both. We further find that factuality (whether a model answers correctly) and honesty (whether a model acknowledges what it does not know) are governed by distinct properties, with high factuality not implying high honesty. To make these findings actionable for non-technical audiences, we release a publicly accessible, user-friendly model overview designed for the full range of stakeholders involved in governmental LLM selection, from engineers to policymakers.

cs.CL↗

arXiv2026

AI From the Margins (AIM): Rethinking Participatory AI Design Through the Lived Experience of Minoritized Communities

Artificial intelligence (AI) can reproduce and amplify the structural inequities faced by minoritized communities. Participatory AI has been proposed as a response, but participation typically starts after problem definitions and success criteria have been set, leaving limited room for minoritized communities to reshape what an AI system is for. We propose AI From the Margins (AIM): a methodological stance that articulates the conditions under which lived experiences of minoritized communities can be elicited, centered, and carried forward to inform participatory AI design. AIM is not a fixed protocol; it articulates a set of preconditions that can be enacted through different techniques in different settings. We applied AIM in a Dutch healthcare context in eight sessions with 13 women and non-binary people of color and five municipal policy workers, namely through (1) narrative elicitation using the Biographic Narrative Interpretive Method (BNIM); (2) co-constructed rule-making; (3) participants' determination of whether, where, and how AI should be involved; and (4) translating lived experience into AI policy through dialogue with policymakers. In their reflections on the sessions, participants described the engagement as substantive and called for its continuation, demonstrating how preparatory orientation fundamentally grounded in lived experience shapes what participatory AI design is for.

cs.CY↗

arXiv2026

Privacy-Aware Visual Language Models

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle privacy-sensitive content is thus essential to protect users. To this end, we conduct a comprehensive evaluation of twelve state-of-the-art VLMs and identify limitations in their understanding of visual privacy. However, existing privacy-related datasets often suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognised visual privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain multiple Privacy VLMs by fine-tuning off-the-shelf VLMs on only a few hundred samples from PrivTune, which leads to substantial gains on all benchmarks, surpassing even GPT-4, while maintaining strong performance on other tasks. Our findings show that privacy-awareness in VLMs can be substantially improved with minimal data and careful dataset design, setting the stage for safer, more privacy-aligned AI systems.

cs.CV↗

arXiv2026

Smart Transportation Without Neurons -- Fair Metro Network Expansion with Tabular Reinforcement Learning

We tackle the Metro Network Expansion Problem (MNEP), a subset of the Transport Network Design Problem (TNDP), which focuses on expanding metro systems to satisfy travel demand. Traditional methods rely on exact and heuristic approaches that require expert-defined constraints to reduce the search space. Recently, deep reinforcement learning (Deep RL) has emerged due to its effectiveness in complex sequential decision-making processes-it remains, however, computationally expensive, environmentally costly, and requires additional engineering to interpret. We show that MNEP problems are small enough to not require Deep RL methods. Reformulating the MNEP as a Non-Markovian Rewards Decision Process (NMRDP), we use tabular RL to achieve similar performance with significantly fewer training episodes, additionally offering greater interpretability. Additionally, we incorporate social equity criteria into the reward functions, focusing on efficiency and fairness, highlighting the versatility of our method. Evaluated in real-world settings-Xi'an and Amsterdam-our method reduces total episodes by a factor of 18 and total carbon emissions by a factor of 12 on average, while remaining competitive with Deep RL. This approach offers a replicable, modular, interpretable, and resource-efficient solution with potential applications to other combinatorial optimization problems.

cs.LG↗

arXiv2026

From Awareness to Action: Understanding and Overcoming the Research-Practice Gap in Algorithmic Fairness for Public Health

Algorithmic fairness is essential for responsible ML-driven public health research, yet its practical implementation remains limited. To investigate this awareness-action gap, we conducted a sequential mixed-methods study comprising expert interviews, an online survey, and systematic mapping. The expert interviews informed the design of the survey, which in turn revealed fragmented definitions of fairness, limited training and guidance, reliance on external sources, and rare use of formal assessment, mitigation, or monitoring. These findings were subsequently mapped onto three established research-practice gap lenses: the Knowledge-Practice Gap, the Knowledge-to-Action Cycle, and the Knowing-Doing Gap, each offering complementary perspectives. Building on this synthesis, we introduce the Fairness-to-Action framework, which integrates methodological, organizational, and systemic dimensions to identify where translation of algorithmic fairness knowledge stalls. Our analysis shows that fairness remains weakly institutionalized, translation mechanisms are externally driven, and system-level priorities continue to emphasize accuracy over fairness. These insights suggest critical leverage points for advancing safe, fair, and ethical ML-driven public health research practice.

cs.CY↗

arXiv2026

Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs

We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (MLLMs). MLLMs are trained to represent vision and language in the same embedding space, yet they cannot perform the same tasks in both modalities. Our benchmarks contain samples with the same semantic information in three modalities (image, text, mixed) and we show that state-of-the-art MLLMs cannot consistently reason over these different modalities. We evaluate 15 MLLMs and find that the degree of modality inconsistency varies substantially, even when accounting for problems with text recognition (OCR). Neither rendering text as image nor rendering an image as text solves the inconsistency. Even if OCR is correct, we find that visual characteristics (text colour and resolution, but not font) and the number of vision tokens have an impact on model performance. Finally, we find that our consistency score correlates with the modality gap between text and images, highlighting a mechanistic interpretation of cross-modal inconsistent MLLMs.

cs.AI↗

arXiv2026

Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance

Multi-Objective Reinforcement Learning (MORL) aims to learn a set of policies that optimize trade-offs between multiple, often conflicting objectives. MORL is computationally more complex than single-objective RL, particularly as the number of objectives increases. Additionally, when objectives involve the preferences of agents or groups, incorporating fairness becomes both important and socially desirable. This paper introduces a principled algorithm that incorporates fairness into MORL while improving scalability to many-objective problems. We propose using Lorenz dominance to identify policies with equitable reward distributions and introduce lambda-Lorenz dominance to enable flexible fairness preferences. We release a new, large-scale real-world transport planning environment and demonstrate that our method encourages the discovery of fair policies, showing improved scalability in two large cities (Xi'an and Amsterdam). Our methods outperform common multi-objective approaches, particularly in high-dimensional objective spaces.

cs.LG↗

arXiv2026

Inequality in Congestion Games with Learning Agents

Who benefits from expanding transport networks? While designed to improve mobility, such interventions can also create inequality. In this paper, we show that disparities arise not only from the structure of the network itself but also from differences in how commuters adapt to it. We model commuters as reinforcement learning agents who adapt their travel choices at different learning rates, reflecting unequal access to resources and information. To capture potential efficiency-fairness tradeoffs, we introduce the Price of Learning (PoL), a measure of inefficiency during learning. We analyze both a stylized network -- inspired in the well-known Braess's paradox, yet with two-source nodes -- and an abstraction of a real-world metro system (Amsterdam). Our simulations show that network expansions can simultaneously increase efficiency and amplify inequality, especially when faster learners disproportionately benefit from new routes before others adapt. These results highlight that transport policies must account not only for equilibrium outcomes but also for the heterogeneous ways commuters adapt, since both shape the balance between efficiency and fairness.

cs.GT↗

arXiv2025

Machine Learning and Public Health: Identifying and Mitigating Algorithmic Bias through a Systematic Review

Machine learning (ML) promises to revolutionize public health through improved surveillance, risk stratification, and resource allocation. However, without systematic attention to algorithmic bias, ML may inadvertently reinforce existing health disparities. We present a systematic literature review of algorithmic bias identification, discussion, and reporting in Dutch public health ML research from 2021 to 2025. To this end, we developed the Risk of Algorithmic Bias Assessment Tool (RABAT) by integrating elements from established frameworks (Cochrane Risk of Bias, PROBAST, Microsoft Responsible AI checklist) and applied it to 35 peer-reviewed studies. Our analysis reveals pervasive gaps: although data sampling and missing data practices are well documented, most studies omit explicit fairness framing, subgroup analyses, and transparent discussion of potential harms. In response, we introduce a four-stage fairness-oriented framework called ACAR (Awareness, Conceptualization, Application, Reporting), with guiding questions derived from our systematic literature review to help researchers address fairness across the ML lifecycle. We conclude with actionable recommendations for public health ML practitioners to consistently consider algorithmic bias and foster transparency, ensuring that algorithmic innovations advance health equity rather than undermine it.

cs.AI↗

arXiv2025

How large language models judge and influence human cooperation

Humans increasingly rely on large language models (LLMs) to support decisions in social settings. Previous work suggests that such tools shape people's moral and political judgements. However, the long-term implications of LLM-based social decision-making remain unknown. How will human cooperation be affected when the assessment of social interactions relies on language models? This is a pressing question, as human cooperation is often driven by indirect reciprocity, reputations, and the capacity to judge interactions of others. Here, we assess how state-of-the-art LLMs judge cooperative actions. We provide 21 different LLMs with an extensive set of examples where individuals cooperate -- or refuse cooperating -- in a range of social contexts, and ask how these interactions should be judged. Furthermore, through an evolutionary game-theoretical model, we evaluate cooperation dynamics in populations where the extracted LLM-driven judgements prevail, assessing the long-term impact of LLMs on human prosociality. We observe a remarkable agreement in evaluating cooperation against good opponents. On the other hand, we notice within- and between-model variance when judging cooperation with ill-reputed individuals. We show that the differences revealed between models can significantly impact the prevalence of cooperation. Finally, we test prompts to steer LLM norms, showing that such interventions can shape LLM judgements, particularly through goal-oriented prompts. Our research connects LLM-based advices and long-term social dynamics, and highlights the need to carefully align LLM norms in order to preserve human cooperation.

physics.soc-ph↗

arXiv2025

EMERGENT: Efficient and Manipulation-resistant Matching using GFlowNets

The design of fair and efficient algorithms for allocating public resources, such as school admissions, housing, or medical residency, has a profound social impact. In one-sided matching problems, where individuals are assigned to items based on ranked preferences, a fundamental trade-off exists between efficiency and strategyproofness. Existing algorithms like Random Serial Dictatorship (RSD), Probabilistic Serial (PS), and Rank Minimization (RM) capture only one side of this trade-off: RSD is strategyproof but inefficient, while PS and RM are efficient but incentivize manipulation. We propose EMERGENT, a novel application of Generative Flow Networks (GFlowNets) to one-sided matching, leveraging its ability to sample diverse, high-reward solutions. In our approach, efficient and manipulation-resistant matches emerge naturally: high-reward solutions yield efficient matches, while the stochasticity of GFlowNets-based outputs reduces incentives for manipulation. Experiments show that EMERGENT outperforms RSD in rank efficiency while significantly reducing strategic vulnerability compared to matches produced by RM and PS. Our work highlights the potential of GFlowNets for applications involving social choice mechanisms, where it is crucial to balance efficiency and manipulability.

cs.LG↗

arXiv2025

Artifacts of Idiosyncracy in Global Street View Data

Street view data is increasingly being used in computer vision applications in recent years. Machine learning datasets are collected for these applications using simple sampling techniques. These datasets are assumed to be a systematic representation of cities, especially when densely sampled. Prior works however, show that there are clear gaps in coverage, with certain cities or regions being covered poorly or not at all. Here we demonstrate that a cities' idiosyncracies, such as city layout, may lead to biases in street view data for 28 cities across the globe, even when they are densely covered. We quantitatively uncover biases in the distribution of coverage of street view data and propose a method for evaluation of such distributions to get better insight in idiosyncracies in a cities' coverage. In addition, we perform a case study of Amsterdam with semi-structured interviews, showing how idiosyncracies of the collection process impact representation of cities and regions and allowing us to address biases at their source.

cs.CV↗

arXiv2025

The Cloud Weaving Model for AI development

While analysing challenges in pilot projects developing AI with marginalized communities, we found it difficult to express them within commonly used paradigms. We therefore constructed an alternative conceptual framework to ground AI development in the social fabric -- the Cloud Weaving Model -- inspired (amongst others) by indigenous knowledge, motifs from nature, and Eastern traditions. This paper introduces and elaborates on the fundamental elements of the model (clouds, spiders, threads, spiderwebs, and weather) and their interpretation in an AI context. The framework is then applied to comprehend patterns observed in co-creation pilots approaching marginalized communities, highlighting neglected yet relevant dimensions for responsible AI development.

cs.CY↗

arXiv2025

EMPLACE: Self-Supervised Urban Scene Change Detection

Urban change is a constant process that influences the perception of neighbourhoods and the lives of the people within them. The field of Urban Scene Change Detection (USCD) aims to capture changes in street scenes using computer vision and can help raise awareness of changes that make it possible to better understand the city and its residents. Traditionally, the field of USCD has used supervised methods with small scale datasets. This constrains methods when applied to new cities, as it requires labour-intensive labeling processes and forces a priori definitions of relevant change. In this paper we introduce AC-1M the largest USCD dataset by far of over 1.1M images, together with EMPLACE, a self-supervising method to train a Vision Transformer using our adaptive triplet loss. We show EMPLACE outperforms SOTA methods both as a pre-training method for linear fine-tuning as well as a zero-shot setting. Lastly, in a case study of Amsterdam, we show that we are able to detect both small and large changes throughout the city and that changes uncovered by EMPLACE, depending on size, correlate with housing prices - which in turn is indicative of inequity.

cs.CV↗

arXiv2024

Analysing and Organising Human Communications for AI Fairness-Related Decisions: Use Cases from the Public Sector

AI algorithms used in the public sector, e.g., for allocating social benefits or predicting fraud, often involve multiple public and private stakeholders at various phases of the algorithm's life-cycle. Communication issues between these diverse stakeholders can lead to misinterpretation and misuse of algorithms. We investigate the communication processes for AI fairness-related decisions by conducting interviews with practitioners working on algorithmic systems in the public sector. By applying qualitative coding analysis, we identify key elements of communication processes that underlie fairness-related human decisions. We analyze the division of roles, tasks, skills, and challenges perceived by stakeholders. We formalize the underlying communication issues within a conceptual framework that i. represents the communication patterns ii. outlines missing elements, such as actors who miss skills for their tasks. The framework is used for describing and analyzing key organizational issues for fairness-related decisions. Three general patterns emerge from the analysis: 1. Policy-makers, civil servants, and domain experts are less involved compared to developers throughout a system's life-cycle. This leads to developers taking on extra roles such as advisor, while they potentially miss the required skills and guidance from domain experts. 2. End-users and policy-makers often lack the technical skills to interpret a system's limitations, and rely on developer roles for making decisions concerning fairness issues. 3. Citizens are structurally absent throughout a system's life-cycle, which may lead to decisions that do not include relevant considerations from impacted stakeholders.

cs.HC↗