Cover Image

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rastogi, Charvi, Teh, Tian Huey, Mishra, Pushkar, Patel, Roma, Wang, Ding, Díaz, Mark, Parrish, Alicia, Davani, Aida Mostafazadeh, Ashwood, Zoe, Paganini, Michela, Prabhakaran, Vinodkumar, Rieser, Verena, Aroyo, Lora
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups
by: Rastogi, Charvi, et al.
Published: (2024)

"Just a strange pic": Evaluating 'safety' in GenAI Image safety annotation tasks from diverse annotators' perspectives
by: Wang, Ding, et al.
Published: (2025)

Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity
by: Mishra, Pushkar, et al.
Published: (2025)

GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives
by: Prabhakaran, Vinodkumar, et al.
Published: (2023)

D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation
by: Davani, Aida Mostafazadeh, et al.
Published: (2024)

GeniL: A Multilingual Dataset on Generalizing Language
by: Davani, Aida Mostafazadeh, et al.
Published: (2024)

Humanlike AI Design Increases Anthropomorphism but Yields Divergent Outcomes on Engagement and Trust Globally
by: Schimmelpfennig, Robin, et al.
Published: (2025)

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models
by: Quaye, Jessica, et al.
Published: (2025)

A Comprehensive Framework to Operationalize Social Stereotypes for Responsible AI Evaluations
by: Davani, Aida, et al.
Published: (2025)

Risks of Cultural Erasure in Large Language Models
by: Qadri, Rida, et al.
Published: (2025)

Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation
by: Denton, Remi, et al.
Published: (2021)

Value Profiles for Encoding Human Variation
by: Sorensen, Taylor, et al.
Published: (2025)

Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI
by: Janowicz, Krzysztof, et al.
Published: (2025)

Taxonomy of User Needs and Actions
by: Shelby, Renee, et al.
Published: (2025)

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
by: Quaye, Jessica, et al.
Published: (2024)

Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
by: Ibrahim, Lujain, et al.
Published: (2025)

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
by: Rastogi, Charvi, et al.
Published: (2026)

Ensemble lagged forecasts of a monsoon depression over India using a mesoscale model
by: Vinodkumar Vinodkumar
Published: (2007)

Bayesian Active Learning for Discrete Latent Variable Models
by: Jha, Aditi, et al.
Published: (2022)

Dataset of the publication: Quantum simulation of wave optics in weakly inhomogeneous media using block-encoding
by: Davani, Siavash
Published: (2026)

SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes
by: Bhutani, Mukul, et al.
Published: (2024)

DIVE: Diversified Iterative Self-Improvement
by: Qin, Yiwei, et al.
Published: (2025)

Towards Geo-Culturally Grounded LLM Generations
by: Lertvittayakumjorn, Piyawat, et al.
Published: (2025)

Kroatisch, katholisch, konservativ
by: Rieser, Rebekka
Published: (2024)

Grothendieck Topologies and Sheaf Theory for Data and Graphs: An Approach Through Cech Closure Spaces
by: Rieser, Antonio
Published: (2021)

A New Construction of the Vietoris-Rips Complex
by: Rieser, Antonio
Published: (2023)

Consistent treatment of quantum systems with a time-dependent Hilbert space
by: Mostafazadeh, Ali
Published: (2024)

A Diophantine Criterion for the Shafarevich-Tate Groups of Elliptic Curves from Heron Triangles
by: Ghale, Vinodkumar
Published: (2023)

Yesterday's News: Benchmarking Multi-Dimensional Out-of-Distribution Generalization of Misinformation Detection Models
by: Verhoeven, Ivo, et al.
Published: (2024)

DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
by: Sun, Xin, et al.
Published: (2024)

"DIVE" into Hydrogen Storage Materials Discovery with AI Agents
by: Zhang, Di, et al.
Published: (2025)

DIVE: Towards Descriptive and Diverse Visual Commonsense Generation
by: Park, Jun-Hyung, et al.
Published: (2024)

DIVE: Taming DINO for Subject-Driven Video Editing
by: Huang, Yi, et al.
Published: (2024)

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
by: Li, Yinqi, et al.
Published: (2025)

Whose Religion? Whose Freedom?
by: Tisa Wenger
Published: (2024)

Evaluation of the Fluence to Dose Conversion Coefficients for High Energy Neutrons Using a Voxel Phantom Coupled with the GEANT4 Code
by: S. Paganini
Published: (2005)

DEAP DIVE: Dataset Investigation with Vision transformers for EEG evaluation
by: Hoffsommer, Annemarie, et al.
Published: (2025)

DIVE: Embedding Compression via Self-Limiting Gradient Updates
by: Zhao, Dongfang
Published: (2026)

Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering
by: Nikandrou, Mavina, et al.
Published: (2022)

TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory
by: Mishra, Pranav Pushkar, et al.
Published: (2025)