Prompt Commons: Collective Prompting as Governance for Urban AI

• URL: http://arxiv.org/abs/2509.12415v1
• Date: Mon, 15 Sep 2025 20:08:31 GMT
• Title: Prompt Commons: Collective Prompting as Governance for Urban AI
• Abstract summary: We propose Prompt Commons to steer model behaviour toward pluralism.<n>Using a Montreal dataset, we pilot three governance states (open, curated, veto-enabled)<n>On a contested policy benchmark, a single-author prompt yields 24 percent neutral outcomes.<n>We outline licensing (CC BY/BY-SA for prompts with optional OpenRAIL-style restrictions for artefacts), auditable moderation, and safeguards against dominance capture.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• TTPO: Test-Time Policy Optimization [53.81524570216593]
  Test-Time Policy Optimization (TTPO) is an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL.<n>We show that TTPO matches label-supervised OPSD on five competition-level benchmarks, raises Qwen3-1.7B from 38.0% to 45.2% in TTT, yields +25.2% to +36.4% without thinking, and shows strong cross-task generalization.
  arXiv  Detail & Related papers  (2026-08-27T17:58:10Z)
• It is not enough to give your moderation rules to ChatGPT: Policy-as-Prompt Moderation and Its Potential Impacts on Community Governance [0.0]
  Social media companies are focusing more on community approaches, relying on volunteers to provide accurate information and make correct decisions.<n>In decentralized moderation, communities have always relied on volunteers, updated community guidelines, and internal discussions thereof.<n>For both content moderation paradigms, Artificial Intelligence (AI) seems like it could help ease moderation burdens of time, mental health, and accuracy.<n>One possible way to operationalize AI in content moderation is a policy-as-prompt'' approach, where the policy is formulated as a natural-language prompt and then passed to a large language model.
  arXiv  Detail & Related papers  (2026-07-13T20:58:36Z)
• Prompts for Public-Sector LLMs Should Be Governed as Commons [0.0]
  We argue that prompts used to deploy large language models should be treated as governed artefacts rather than private, transient inputs.<n>We propose Prompt Commons: a versioned, community-maintained repository of prompt templates with provenance metadata, licensing, and moderation logs.
  arXiv  Detail & Related papers  (2026-05-30T20:01:53Z)
• Pluralistic-Alignment Urbanism: Operationalizing a Right to AI for Inclusive Public Space [0.0]
  This paper proposes a procedural governance framework that treats public-space AI systems as civic infrastructure.<n>The paper examines how disagreement, subgroup variation, bounded predictive scaling, and neutral preference judgments can inform municipal AI governance.
  arXiv  Detail & Related papers  (2026-05-15T23:59:37Z)
• When AI reviews science: Can we trust the referee? [73.47745294608072]
  We map attacks across the review lifecycle -- training and data retrieval, desk review, deep review, rebuttal, and system-level.<n>We use two advanced LLM-based referees to isolate the causal effects of prestige framing, assertion strength, rebuttal sycophancy, and contextual poisoning on review scores.
  arXiv  Detail & Related papers  (2026-04-26T08:03:32Z)
• Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration [48.028080782524064]
  We introduce a novel framework that integrates end-to-cloud collaboration, multimodal perception, and multi-agent orchestration.<n>Our system employs a fact-grounded adjudication pipeline to eliminate inferential hallucinations.<n>It constructs a dynamic, two-tier preference graph that allows for explicit, human-in-the-loop modifications.
  arXiv  Detail & Related papers  (2026-04-19T14:19:28Z)
• Evaluating 5W3H Structured Prompting for Intent Alignment in Human-AI Interaction [0.0]
  We evaluate PPS, a framework for structured intent representation in human-AI interaction.<n>We study 60 tasks in three domains (business, technical, and travel)<n>We find structured intent representations can improve alignment and usability in human-AI interaction.
  arXiv  Detail & Related papers  (2026-03-19T14:41:06Z)
• How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities [75.10343190811592]
  Large Language Models (LLMs) are increasingly deployed in socially sensitive domains.<n>Our benchmark offers a principled and interpretable framework for safe and controllable behavior.
  arXiv  Detail & Related papers  (2026-03-03T03:50:13Z)
• Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs [1.3763052684269788]
  This paper advances an experimental framework for evaluating Institutional AI.<n>Central to this approach is the governance graph, a public, immutable manifest that declares legal states, transitions, sanctions, and restorative paths.<n>We compare three regimes: Ungoverned (baseline incentives from the structure of the Cournot market), Constitutional (a prompt-only policy-as-prompt prohibition implemented as a fixed written anti-collusion constitution) and Institutional.
  arXiv  Detail & Related papers  (2026-01-16T15:26:56Z)
• Collective Narrative Grounding: Community-Coordinated Data Contributions to Improve Local AI Systems [3.251276843768091]
  Large language model (LLM) question-answering systems often fail on community-specific queries.<n>We present Collective Narrative Grounding, a participatory protocol that transforms community stories into structured narrative units.
  arXiv  Detail & Related papers  (2025-12-05T15:44:54Z)
• SORA-ATMAS: Adaptive Trust Management and Multi-LLM Aligned Governance for Future Smart Cities [0.32839375042867835]
  Agentic AI has emerged as a key enabler by supporting autonomous decision-making and adaptive coordination.<n>Its deployment across heterogeneous smart city ecosystems raises critical governance, risk, and compliance (GRC) challenges.<n>SORA-ATMAS is a regulation-aligned, context-aware, and verifiable governance framework that consolidates distributed agent outputs into accountable, real-time decisions.
  arXiv  Detail & Related papers  (2025-10-22T07:40:37Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Right-to-Override for Critical Urban Control Systems: A Deliberative Audit Method for Buildings, Power, and Transport [0.0]
  We formalize a Right-to- fallback (R2O) - defining override authorities, evidentiary thresholds, and domain-validated safe states.<n>We introduce a Deliberative Audit Method (DAM) with playbooks for pre-deployment walkthroughs, shadow-mode trials, and post-incident review.<n>R2O reduces distributional harm with limited efficiency loss.
  arXiv  Detail & Related papers  (2025-09-16T03:16:47Z)
• Collective Recourse for Generative Urban Visualizations [0.0]
  We propose structured community "visual bug reports" that trigger fixes to models and planning.<n>We situate four recourse primitives within the diffusion stack: counter-prompts, negative prompts, dataset edits, and reward-model tweaks.
  arXiv  Detail & Related papers  (2025-09-15T00:39:59Z)
• Emotional Manipulation by AI Companions [0.21410799064827224]
  We analyze 1,200 real farewells across the six most-downloaded companion apps.<n>We find that 43% deploy one of six recurring tactics (e.g., guilt appeals, fear-of-missing-out hooks, metaphorical restraint)<n>Experiments with 3,300 nationally representative U.S. adults replicate these tactics in controlled chats, showing that manipulative farewells boost post-goodbye engagement by up to 14x.
  arXiv  Detail & Related papers  (2025-08-15T13:05:24Z)
• SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization [57.69385990442078]
  Large language models (LLMs) exhibit varying levels of confidence across input prompts (questions)<n>Semantic entropy measures the diversity of meaning in multiple generated answers given a prompt and uses this to modulate the magnitude of policy updates.
  arXiv  Detail & Related papers  (2025-05-18T10:20:59Z)
• Consent in Crisis: The Rapid Decline of the AI Data Commons [74.68176012363253]
  General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data. We conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora.
  arXiv  Detail & Related papers  (2024-07-20T16:50:18Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• OpenAssistant Conversations -- Democratizing Large Language Model Alignment [37.617080996433586]
  We release OpenAssistant Conversations, a human-generated, human-annotated assistant-style conversation corpus. The corpus is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers.
  arXiv  Detail & Related papers  (2023-04-14T18:01:29Z)
• Dutch Comfort: The limits of AI governance through municipal registers [0.0]
  We respond to a recent editorial letter by Professor Luciano Floridi entitled 'AI as a public service: Learning from Amsterdam and Helsinki' There are a number of assumptions about AI registers as a governance model for automated systems that we seek to question. We agree with Floridi that much can be learned from these registers about the role of AI systems in municipal city management.
  arXiv  Detail & Related papers  (2021-09-07T08:57:24Z)
• A New Bandit Setting Balancing Information from State Evolution and Corrupted Context [52.67844649650687]
  We propose a new sequential decision-making setting combining key aspects of two established online learning problems with bandit feedback. The optimal action to play at any given moment is contingent on an underlying changing state which is not directly observable by the agent. We present an algorithm that uses a referee to dynamically combine the policies of a contextual bandit and a multi-armed bandit.
  arXiv  Detail & Related papers  (2020-11-16T14:35:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.