Prompt Commons: Collective Prompting as Governance for Urban AI

2025-09-15

AI Summary

Large language models (LLMs) deployed in urban governance are vulnerable to value-laden prompts, leading to output bias and ideological homogenization. To address this, we propose “Prompt Co-Governance”: a versioned, community-driven prompt repository integrating governance metadata, tiered licensing (CC BY/BY-SA + OpenRAIL), auditable review mechanisms, and anti-monopoly design. Piloted on the Montreal Urban Dataset, it enables three governance modalities—open review, crowdsourced auditing, and user veto. Leveraging prompt versioning, synthetic event log analysis, and human-AI collaborative evaluation, our framework significantly improves neutrality and responsiveness in AI policy support: neutral outputs increase from 24% to 48–52%, and harmful response mitigation time decreases from 30.5 to 5.6 hours. This work pioneers the systematic transformation of prompt engineering into governance infrastructure for value alignment in municipal AI systems.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large Language Models (LLMs) are entering urban governance, yet their outputs are highly sensitive to prompts that carry value judgments. We propose Prompt Commons - a versioned, community-maintained repository of prompts with governance metadata, licensing, and moderation - to steer model behaviour toward pluralism. Using a Montreal dataset (443 human prompts; 3,317 after augmentation), we pilot three governance states (open, curated, veto-enabled). On a contested policy benchmark, a single-author prompt yields 24 percent neutral outcomes; commons-governed prompts raise neutrality to 48-52 percent while retaining decisiveness where appropriate. In a synthetic incident log, a veto-enabled regime reduces time-to-remediation for harmful outputs from 30.5 +/- 8.9 hours (open) to 5.6 +/- 1.5 hours. We outline licensing (CC BY/BY-SA for prompts with optional OpenRAIL-style restrictions for artefacts), auditable moderation, and safeguards against dominance capture. Prompt governance offers a practical lever for cities to align AI with local values and accountability.

Problem

• Managing value sensitivity in urban AI prompts
• Ensuring pluralistic outcomes in policy decision-making
• Reducing remediation time for harmful AI outputs

Innovation

• Community-maintained repository with governance metadata
• Piloting three governance states for prompts
• Licensing and moderation to ensure pluralism