Research Papers

The increasing adoption of AI systems in hiring has raised concerns about algorithmic bias and accountability, prompting regulatory responses including the EU AI Act, NYC Local Law 144, and Colorado's AI Act. While existing research examines bias through technical or regulatory lenses, both perspectives overlook a fundamental challenge: modern AI hiring systems operate within complex supply chains where responsibility fragments across data vendors, model developers, platform providers, and deploying organizations. This paper investigates how these dependency chains complicate bias evaluation and accountability attribution. Drawing on literature review and regulatory analysis, we demonstrate that fragmented responsibilities create two critical problems. First, bias emerges from component interactions rather than isolated elements, yet proprietary configurations prevent integrated evaluation. A resume parser may function without bias independently but contribute to discrimination when integrated with specific ranking algorithms and filtering thresholds. Second, information asymmetries mean deploying organizations bear legal responsibility without technical visibility into vendor-supplied algorithms, while vendors control implementations without meaningful disclosure requirements. Each stakeholder may believe they are compliant; nevertheless, the integrated system may produce biased outcomes. Analysis of implementation ambiguities reveals these challenges in practice. We propose multi-layered interventions including system-level audits, vendor guidelines, continuous monitoring mechanisms, and documentation across dependency chains. Our findings reveal that effective governance requires coordinated action across technical, organizational, and regulatory domains to establish meaningful accountability in distributed development environments.

Beyond Semantic Similarity: A Component-Wise Evaluation Framework for Medical Question Answering Systems with Health Equity Implications

Abu Noman Md Sakib, Md. Main Oddin Chisty, Zijie Zhang

The use of Large Language Models (LLMs) to support patients in addressing medical questions is becoming increasingly prevalent. However, most of the measures currently used to evaluate the performance of these models in this context only measure how closely a model's answers match semantically, and therefore do not provide a true indication of the model's medical accuracy or of the health equity risks associated with it. To address these shortcomings, we present a new evaluation framework for medical question answering called VB-Score (Verification-Based Score) that provides a separate evaluation of the four components of entity recognition, semantic similarity, factual consistency, and structured information completeness for medical question-answering models. We perform rigorous reviews of the performance of three well-known and widely used LLMs on 48 public health-related topics taken from high-quality, authoritative information sources. Based on our analyses, we discover a major discrepancy between the models' semantic and entity accuracy. Our assessments of the performance of all three models show that each of them has almost uniformly severe performance failures when evaluated against our criteria. Our findings indicate alarming performance disparities across various public health topics, with most of the models exhibiting 13.8% lower performance (compared to an overall average) for all the public health topics that relate to chronic conditions that occur in older and minority populations, which indicates the existence of what's known as condition-based algorithmic discrimination. Our findings also demonstrate that prompt engineering alone does not compensate for basic architectural limitations on how these models perform in extracting medical entities and raise the question of whether semantic evaluation alone is a sufficient measure of medical AI safety.

Because artificial intelligence (AI) increasingly mediates organizational work, fairness has become a critical governance challenge. Existing frameworks often prioritize abstract ethical principles rather than fairness-specific ones and lack actionable guidance across the entire AI lifecycle. This study addresses the principles-to-practice gap in AI fairness governance. We develop actionable AI fairness practices and draw on a socio-technical and praxiological lens, conducting discourse and thematic analyses of 60 academic, policy, and practitioner sources. From these analyses, we derive a structured set of AI fairness practices in a comprehensive, AI lifecycle-spanning matrix organized by obligation degree and organizational role. The matrix provides dynamic, role-specific guidance to support implementation and sustainment of AI fairness. By extending the AI fairness beyond abstract principles to operationalized, actionable practices, we contribute to IS scholarship and offer a modular governance scaffold.

Large Language Models (LLMs) are increasingly used to generate narrative content, including children's stories, which play an important role in social and cultural learning. Despite growing interest in AI safety and alignment, most existing evaluations focus primarily on English, leaving the cross-lingual generalization of aligned behavior underexplored. In this work, we introduce BiasedTales-ML, a large-scale parallel corpus of approximately 350,000 children's stories generated across eight typologically and culturally diverse languages using a full-permutation prompting design. We propose a structured generator-extractor pipeline and a multi-dimensional distributional analysis framework to examine how narrative attributes vary across languages, models, and social conditions. Our analysis reveals substantial cross-lingual variability in narrative generation patterns, indicating that distributions observed in English do not always exhibit similar characteristics in other languages, particularly in lower-resource settings. At the narrative level, we identify recurring structural patterns involving character roles, settings, and thematic emphasis, which manifest differently across linguistic contexts. These findings highlight the limitations of English-centric evaluation for characterizing socially grounded narrative generation in multilingual settings. We release the dataset, code, and an interactive visualization tool to support future research on multilingual narrative analysis and evaluation.

Rapid advances in Generative AI are giving rise to increasingly sophisticated Multi-Agent AI (MAAI) systems. While AI fairness has been extensively studied in traditional predictive scenarios, its examination in MAAI remains nascent and fragmented. This scoping review critically synthesizes existing research on fairness in MAAI systems. Through a qualitative content analysis of 23 selected studies, we identify five archetypal approaches. Our findings reveal that fairness in MAAI systems is often addressed superficially, lacks robust normative foundations, and frequently overlooks the complex dynamics introduced by agent autonomy and system-level interactions. We argue that fairness must be embedded structurally throughout the development lifecycle of MAAI, rather than appended as a post-hoc consideration. Meaningful evaluation requires explicit human oversight, normative clarity, and a precise articulation of fairness objectives and beneficiaries. This review provides a foundation for advancing fairness research in MAAI systems by highlighting critical gaps, exposing prevailing limitations, and suggesting pathways.

Artificial intelligence (AI) is increasingly reshaping lifelong learning by introducing new possibilities for personalized, flexible, and data-informed educational practices. In the field of adult education, AI has gained particular importance as learners are expected to continuously update their knowledge and skills in response to rapid technological, economic, and social change. This paper examines the role of AI in adult education policy, with a focus on both its opportunities and its challenges. It discusses how AI can support personalized learning, intelligent tutoring, learning analytics, and workforce development, while also contributing to greater accessibility, scalability, and policy responsiveness. At the same time, the paper highlights significant concerns related to the digital divide, data privacy, algorithmic bias, over-reliance on technology, and the readiness of educators and institutions to integrate AI effectively. Drawing on contemporary literature and international policy frameworks, the paper argues that AI should not be approached simply as a technological solution, but as a socio-technical and ethical issue that requires careful governance. It concludes that the successful integration of AI into lifelong learning depends on balanced adult education policies that promote inclusion, transparency, human-centered pedagogy, and responsible innovation.

Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance

Matteo Wohlrapp, Niklas Bubeck, Daniel Rueckert +1

AI-based image reconstruction models are increasingly deployed in clinical workflows to improve image quality from noisy data, such as low-dose X-rays or accelerated MRI scans. However, these models are typically evaluated using pixel-level metrics like PSNR, leaving their impact on downstream diagnostic performance and fairness unclear. We introduce a scalable evaluation framework that applies reconstruction and diagnostic AI models in tandem, which we apply to two tasks (classification, segmentation), three reconstruction approaches (U-Net, GAN, diffusion), and two data types (X-ray, MRI) to assess the potential downstream implications of reconstruction. We find that conventional reconstruction metrics poorly track task performance, where diagnostic accuracy remains largely stable even as reconstruction PSNR declines with increasing image noise. Fairness metrics exhibit greater variability, with reconstruction sometimes amplifying demographic biases, particularly regarding patient sex. However, the overall magnitude of this additional bias is modest compared to the inherent biases already present in diagnostic models. To explore potential bias mitigation, we adapt two strategies from classification literature to the reconstruction setting, but observe limited efficacy. Overall, our findings emphasize the importance of holistic performance and fairness assessments throughout the entire medical imaging workflow, especially as generative reconstruction models are increasingly deployed.

Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models

Syed Rifat Raiyan

The Identifiable Victim Effect (IVE) $-$ the tendency to allocate greater resources to a specific, narratively described victim than to a statistically characterized group facing equivalent hardship $-$ is one of the most robust findings in moral psychology and behavioural economics. As large language models (LLMs) assume consequential roles in humanitarian triage, automated grant evaluation, and content moderation, a critical question arises: do these systems inherit the affective irrationalities present in human moral reasoning? We present the first systematic, large-scale empirical investigation of the IVE in LLMs, comprising N=51,955 validated API trials across 16 frontier models spanning nine organizational lineages (Google, Anthropic, OpenAI, Meta, DeepSeek, xAI, Alibaba, IBM, and Moonshot). Using a suite of ten experiments $-$ porting and extending canonical paradigms from Small et al. (2007) and Kogut and Ritov (2005) $-$ we find that the IVE is prevalent but strongly modulated by alignment training. Instruction-tuned models exhibit extreme IVE (Cohen's d up to 1.56), while reasoning-specialized models invert the effect (down to d=-0.85). The pooled effect (d=0.223, p=2e-6) is approximately twice the single-victim human meta-analytic baseline (d$\approx$0.10) reported by Lee and Feeley (2016) $-$ and likely exceeds the overall human pooled effect by a larger margin, given that the group-victim human effect is near zero. Standard Chain-of-Thought (CoT) prompting $-$ contrary to its role as a deliberative corrective $-$ nearly triples the IVE effect size (from d=0.15 to d=0.41), while only utilitarian CoT reliably eliminates it. We further document psychophysical numbing, perfect quantity neglect, and marginal in-group/out-group cultural bias, with implications for AI deployment in humanitarian and ethical decision-making contexts.

Bail decisions present a fundamental challenge for data-driven decision support systems. When bail is denied, the counterfactual outcome of whether the defendant would have appeared in court remains unobserved. As a result, historical bail data embed structural label indeterminacy: future decisions are influenced by past decisions whose outcomes are only partially knowable. Building automated systems on such data risks introducing bias and reinforcing feedback loops. This raises a core question for machine-learning systems intended to assist judicial actors: how should cases in which bail was denied be treated during model development? In a case study of bail decisions from the Unified Judicial System of Pennsylvania, we evaluate five contemporary approaches to handling label indeterminacy across three machine learning models, including a novel label imputation method motivated by the dynamics of bail decisions. Each method relies on unverifiable assumptions, yet all influence the models' predictive behaviour, sometimes even more so than the choice of model itself. Explainable AI analysis further reveals that these effects extend to the models' internal decision-making processes as well. Finally, we consider the notion of label indeterminacy from a legal perspective and assess the legitimacy of these approaches in the context of bail decision-making.

Transformer-based large language models (LLMs) and multi-agent systems (MAS) are increasingly embedded across the software development lifecycle (SDLC), yet their fairness implications for developer-facing tools remain underexplored despite their growing role in shaping what code is written, reviewed, and released. We present a rapid review of recent work on fairness in MAS, emphasizing LLM-enabled settings and relevance to software engineering. Starting from an initial set of 350 papers, we screened and filtered the corpus for relevance, retaining 18 studies for final analysis. Across these 18 studies, fairness is framed as a combination of trustworthy AI principles, bias reduction across groups, and interactional dynamics in collectives, while evaluation spans accuracy metrics on bias benchmarks, demographic disparity measures, and emergent MAS-specific notions such as conformity and bias amplification. Reported harms include representational, quality-of-service, security and privacy, and governance failures, which we relate to SDLC stages where evidence is most and least developed. We identify three persistent gaps: (1) fragmented, rarely MAS-specific evaluation practices that limit comparability, (2) limited generalization due to simplified environments and narrow attribute coverage, and (3) scarce, weakly evaluated mitigation and governance mechanisms aligned to real software workflows. These findings suggest MAS fairness research is not yet ready to support deployable, fairness-assured software systems, motivating MAS-aware benchmarks, consistent protocols, and lifecycle-spanning governance.

No feature ranking can be simultaneously faithful, stable, and complete when features are collinear. For collinear pairs, ranking reduces to a coin flip. We prove this impossibility, quantify it for four model classes, resolve it via ensemble averaging (DASH), and machine-verify it with 305 Lean 4 theorems. We characterize the complete attribution design space: exactly two families of methods exist -- faithful-complete methods (unstable, with rankings that flip up to 50% of the time) and ensemble methods like DASH (stable, reporting ties for symmetric features) -- and no method lies outside this dichotomy. The impossibility is quantitative: the attribution ratio diverges as 1/(1-rho^2) for gradient boosting, is infinite for Lasso, and converges for random forests. DASH (Diversified Aggregation of SHAP) is provably Pareto-optimal among unbiased aggregations, achieving the Cramer-Rao variance bound with a tight ensemble size formula. In a survey of 77 public datasets, 68% exhibit attribution instability. Switching to conditional SHAP does not escape the impossibility when features have equal causal effects. The framework includes practical diagnostics -- a Z-test workflow and single-model screening tool -- and has direct consequences for fairness auditing: SHAP-based proxy discrimination audits are provably unreliable under collinearity. The design space theorem, diagnostics, and impossibility are mechanically verified in Lean 4 (305 theorems from 16 axioms, 0 sorry) -- to our knowledge, the first formally verified impossibility in explainable AI.

Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality. We present a satellite-reanalysis PM2.5 fusion system trained on 2,068,901 records from 404 monitoring locations in 29 African countries (OpenAQ, 2017-2022), combining LightGBM with leakage-resistant spatial cross-validation and conformal prediction to quantify predictions and their geographic applicability limits. Under 5-fold location-grouped spatial cross-validation, LightGBM achieves RMSE = 30.83 +/- 5.07 ug/m3, MAE = 14.54 +/- 1.66 ug/m3, R2 = 0.134 +/- 0.023, and macro F1 = 0.336 +/- 0.018. This R2 is substantially below random-split benchmarks (>0.90) but reflects true geographic generalisation difficulty rather than model failure. Split conformal prediction targeting 90% marginal coverage reveals severe East Africa degradation (actual PICP = 65.3% vs. nominal 90%), consistent with medium-strength covariate shift (humidity KS = 0.2237, sat_pblh KS = 0.2558). We operationalise these findings through regional reliability flags (High/Medium/Low/Unreliable) and a monitor prioritisation score directing infrastructure expansion toward highest-burden unmonitored populations, directly supporting Africa's green industrial transition and SDGs 3.9, 7.1.2, 9, 11.6.2, and 13.