mlsanityData to 7 Oct 2026

Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies

arXiv 2503.12613 ↗First posted 16 Mar 2025cs.HC cs.AI cs.CYcited by 4

Not on the map. Why?

Abstract (arXiv)

Urban assessments often compress diverse needs into single scores, which can obscure minority perspectives. We present a community-centered study in Montreal (n=35; wheelchair users, seniors, LGBTQIA2+ residents, and immigrants). Participants rated 20 streets (accessibility, inclusivity, aesthetics, practicality) and ranked 7 images on 12 interview-elicited criteria. Disagreement patterns were systematic in our sample: wheelchair users diverged most on accessibility and practicality; LGBTQIA2+ participants emphasized inclusion and liveliness; seniors prioritized security. Group discussion reduced information gaps but not value conflicts; ratings conveyed intensity, while rankings forced trade-offs. We then formalize negotiative alignment, a transparent, budget-aware bargaining procedure, and pilot it with role-played stakeholder agents plus a neutral mediator. Relative to the best base design under the same public rubric, the negotiated package increased total utility (21.10 to 24.55), raised the worst-group utility (3.20 to 3.90), improved twentieth percentile satisfaction (0.86 to 1.00; min-max normalized within the scenario), and reduced inequality (Gini 0.036 to 0.025). Treating disagreement as signal and reporting worst-group outcomes alongside totals may help planners and AI practitioners surface trade-offs and preserve minority priorities while maintaining efficiency.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 80 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

19 of 80 references.

References · 19

  1. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  2. 2020Artificial Intelligence, Values and Alignmentcited by 443
  3. 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Modelscited by 136
  4. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  5. 2023Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategiescited by 83
  6. 2024Beyond Preferences in AI Alignmentcited by 46
  7. 2024Large Language Model for Participatory Urban Planningcited by 40
  8. 2018CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learningcited by 31
  9. 2022Vote'n'Rank: Revision of Benchmarking with Social Choice Theorycited by 15
  10. 2023Algorithmic Pluralism: A Structural Approach To Equal Opportunitycited by 13
  11. 2021Goldilocks: Consistent Crowdsourced Scalar Annotations with Relative Uncertaintycited by 12
  12. 2024LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop Participatory Urban Planningcited by 8
7 more
  1. 2025LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spacescited by 8
  2. 2023AI Agent as Urban Planner: Steering Stakeholder Dynamics in Urban Planning via Consensus-based Multi-Agent Reinforcement Learningcited by 4
  3. 2024Survey of Distributed Algorithms for Resource Allocation over Multi-Agent Systemscited by 4
  4. 2025The Right to AIcited by 3
  5. 2024Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Predictioncited by 2
  6. 2021Dynamic Urban Planning: an Agent-Based Model Coupling Mobility Mode and Housing Choice. Use case Kendall Squarecited by 1
  7. 2024AI-EDI-SPACE: A Co-designed Dataset for Evaluating the Quality of Public Spacescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.