arXiv AI
Equity Bias: An Ethical Framework for AI Design
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
2d ago
Beyond the principle-practice gap: Responsible AI as situated epistemic and ethical practice
The paper argues that the commonly cited gap between ethical principles and AI practice is not merely a matter of implementation or compliance, but arises from the complex institutional and professional contexts in which AI actors operate. Through interviews with designers and governors of anti‑trafficking AI systems, it identifies four interconnected moments—perception, judgement, situated action, and socio‑technical materialisation—through which ethical concerns are recognised, weighed, and either realised or sidelined. The authors contend that responsible AI governance must build epistemic infrastructures that transcend these constraints, enabling the knowledge of affected communities and potential harms to be effectively integrated into design and governance.
arXiv AI
Aug 13
Variable Selection in the Context of AI Fairness
arXiv:2608. 11251v1 Announce Type: cross Abstract: Fairness in AI systems has become more important with recent regulatory demands, such as the EU AI Act.
arXiv AI
Aug 18
The Benchmark Trap: Structures of Power and Injustice in AI Evaluations
arXiv:2608. 15326v1 Announce Type: new Abstract: Artificial intelligence (AI) benchmarks are not neutral tools of evaluation but socio-technical artefacts that shape competition, power, and research priorities within AI.
arXiv AI
Sep 3
Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
The paper examines how the rise of AI capable of moral reasoning could reshape meta-ethics, traditionally focused on human ethics. It proposes a framework that identifies new questions about AI’s own ethics from both human and AI perspectives, dividing them into four domains. The author explores how existing meta-ethical theories might apply to these domains and argues that many human-centered formulations will need significant revision to accommodate AI.
arXiv AI
Sep 23
Biased AI improves human performance but reduces perceived helpfulness
The study tests deliberately biased AI assistants and finds that such bias improves human performance on tasks like misinformation evaluation, financial investment, and graduate education compared to neutral AI. However, participants undervalue biased AI and overvalue neutral AI, even when performance is similar. When two AI biases flank a participant’s perspective, performance gains are maintained while reducing the perceived cost and one‑sided influence.
arXiv AI
Jul 9
Towards Agentic AI Governance: A Preliminary Assessment
arXiv:2607. 07612v1 Announce Type: cross Abstract: Artificial intelligence is rapidly evolving from generative systems to agentic AI capable of autonomously planning and executing tasks.