# LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces arXiv: https://arxiv.org/abs/2503.01894 ยท HTML: https://mlsanity.com/paper/2503.01894/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. - Builds on 26 of its 72 references that are in the map. - First posted on arXiv 27 Feb 2025. ## Placed in - LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/) ## Builds on (most cited first, 26 of 26) - [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018) - [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023) - [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023) - [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023) - [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023) - [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023) - [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023) - [Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages](https://mlsanity.com/paper/2010.02353/) (2020) - [Collective Constitutional AI: Aligning a Language Model with Public Input](https://mlsanity.com/paper/2406.07814/) (2024) - [Participation is not a Design Fix for Machine Learning](https://mlsanity.com/paper/2007.02423/) (2020) - [Learning Multi-dimensional Human Preference for Text-to-Image Generation](https://mlsanity.com/paper/2405.14705/) (2024) - [Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence](https://mlsanity.com/paper/2007.04068/) (2020) - [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024) - [Human Feedback is not Gold Standard](https://mlsanity.com/paper/2309.16349/) (2023) - [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024) - [AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia](https://mlsanity.com/paper/2305.11844/) (2023) - [Language Model Alignment in Multilingual Trolley Problems](https://mlsanity.com/paper/2407.02273/) (2024) - [The Challenge of Value Alignment: from Fairer Algorithms to AI Safety](https://mlsanity.com/paper/2101.06060/) (2021) - [The illusion of artificial inclusion](https://mlsanity.com/paper/2401.08572/) (2024) - [Aligning Crowd Feedback via Distributional Preference Reward Modeling](https://mlsanity.com/paper/2402.09764/) (2024) - [Preference learning along multiple criteria: A game-theoretic perspective](https://mlsanity.com/paper/2105.01850/) (2021) - [A preference learning framework for multiple criteria sorting with diverse additive value models and valued assignment examples](https://mlsanity.com/paper/1910.05485/) (2019) - [Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI](https://mlsanity.com/paper/2410.23630/) (2024) - [From Fake Perfects to Conversational Imperfects: Exploring Image-Generative AI as a Boundary Object for Participatory Design of Public Spaces](https://mlsanity.com/paper/2411.00949/) (2024) ## Built on by (most cited first, 8 of 8) - [CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics](https://mlsanity.com/paper/2506.08835/) (2025) - [Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies](https://mlsanity.com/paper/2503.12613/) (2025) - [Do Vision-Language Models See Urban Scenes as People Do? An Urban Perception Benchmark](https://mlsanity.com/paper/2509.14574/) (2025) - [Street Review: A Participatory AI-Based Framework for Assessing Streetscape Inclusivity](https://mlsanity.com/paper/2508.11708/) (2025) - [Co-Producing AI: Toward an Augmented, Participatory Lifecycle](https://mlsanity.com/paper/2508.00138/) (2025) - [Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated](https://mlsanity.com/paper/2606.00871/) (2026) - [Traceable, Enforceable, and Compensable Participation: A Participation Ledger for People-Centered AI Governance](https://mlsanity.com/paper/2602.10916/) (2026) - [AI Pluralism and the Worlds It Misses](https://mlsanity.com/paper/2606.16167/) (2026) ## Abstract (arXiv) We introduce the Local Intersectional Visual Spaces (LIVS) dataset, a benchmark for multi-criteria alignment, developed through a two-year participatory process with 30 community organizations to support the pluralistic alignment of text-to-image (T2I) models in inclusive urban planning. The dataset encodes 37,710 pairwise comparisons across 13,462 images, structured along six criteria - Accessibility, Safety, Comfort, Invitingness, Inclusivity, and Diversity - derived from 634 community-defined concepts. Using Direct Preference Optimization (DPO), we fine-tune Stable Diffusion XL to reflect multi-criteria spatial preferences and evaluate the LIVS dataset and the fine-tuned model through four case studies: (1) DPO increases alignment with annotated preferences, particularly when annotation volume is high; (2) preference patterns vary across participant identities, underscoring the need for intersectional data; (3) human-authored prompts generate more distinctive visual outputs than LLM-generated ones, influencing annotation decisiveness; and (4) intersectional groups assign systematically different ratings across criteria, revealing the limitations of single-objective alignment. While DPO improves alignment under specific conditions, the prevalence of neutral ratings indicates that community values are heterogeneous and often ambiguous. LIVS provides a benchmark for developing T2I models that incorporate local, stakeholder-driven preferences, offering a foundation for context-aware alignment in spatial design.