可信 AI 与民主：民主风险与贡献的双重分类及操作框架

View PDF HTML (experimental)

Abstract:Artificial Intelligence (AI) can undermine and strengthen democratic governance. This paper introduces the AIRD/AIPD framework, a dual taxonomy and operational framework for analyzing AI's democratic risks and conditional contributions. The AI Risks to Democracy (AIRD) taxonomy identifies threats to autonomy, fairness, public discourse, democratic institutions, and trust, while the AI's Positive Contributions to Democracy (AIPD) taxonomy captures AI's potential to enhance efficiency, accessibility, security, informed citizenry, transparency and accountability, inclusive democratic dialogue, and evidence-based policymaking. Grounded in five democratic principles and the seven Trustworthy AI requirements proposed by the European Commission's High-Level Expert Group on AI, the framework connects democratic goals with governance and design mechanisms. It provides an operational process for identifying affected contexts and actors, classifying primary and secondary AIRD/AIPD effects, mapping them to relevant Trustworthy AI requirements, and defining proportionate governance responses and responsible actors. An operational mapping and two worked examples illustrate its application to electoral misinformation and AI-assisted public service allocation. The analysis highlights the transversal relevance of transparency, accountability, fairness, and societal wellbeing, while recognizing trade-offs, implementation costs, differential impacts, institutional capacity, and contextual variation across democratic settings. The framework is conceptual and has not been empirically validated, but it offers a traceable and adaptable basis for research, policy analysis, institutional oversight, and responsible AI design. By connecting democratic diagnosis with governance action, it bridges the gap between normative principles and the operational requirements of trustworthy and democratically legitimate AI.

Comments:	26 pages, 5 figures
Subjects:	Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
Cite as:	arXiv:2505.13565 [cs.CY]
	(or arXiv:2505.13565v3 [cs.CY] for this version)
	https://doi.org/10.48550/arXiv.2505.13565 arXiv-issued DOI via DataCite
Related DOI:	https://doi.org/10.1109/TSMC.2026.3743429 DOI(s) linking to related resources

Submission history

From: Oier Mentxaka [view email]
[v1] Mon, 19 May 2025 10:51:08 UTC (855 KB)
[v2] Tue, 13 Jan 2026 11:40:27 UTC (763 KB)
[v3] Thu, 29 Oct 2026 08:30:03 UTC (773 KB)