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

• URL: http://arxiv.org/abs/2507.13383v1
• Date: Tue, 15 Jul 2025 21:02:35 GMT
• Title: Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
• Authors: Charvi Rastogi, Tian Huey Teh, Pushkar Mishra, Roma Patel, Ding Wang, Mark Díaz, Alicia Parrish, Aida Mostafazadeh Davani, Zoe Ashwood, Michela Paganini, Vinodkumar Prabhakaran, Verena Rieser, Lora Aroyo,
• Abstract summary: Current text-to-image (T2I) models often fail to account for diverse human experiences, leading to misaligned systems.<n>We advocate for pluralistic alignment, where an AI understands and is steerable towards diverse, and often conflicting, human values.
• Score: 29.501859416167385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current text-to-image (T2I) models often fail to account for diverse human experiences, leading to misaligned systems. We advocate for pluralistic alignment, where an AI understands and is steerable towards diverse, and often conflicting, human values. Our work provides three core contributions to achieve this in T2I models. First, we introduce a novel dataset for Diverse Intersectional Visual Evaluation (DIVE) -- the first multimodal dataset for pluralistic alignment. It enable deep alignment to diverse safety perspectives through a large pool of demographically intersectional human raters who provided extensive feedback across 1000 prompts, with high replication, capturing nuanced safety perceptions. Second, we empirically confirm demographics as a crucial proxy for diverse viewpoints in this domain, revealing significant, context-dependent differences in harm perception that diverge from conventional evaluations. Finally, we discuss implications for building aligned T2I models, including efficient data collection strategies, LLM judgment capabilities, and model steerability towards diverse perspectives. This research offers foundational tools for more equitable and aligned T2I systems. Content Warning: The paper includes sensitive content that may be harmful.

Related papers

• Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? [81.49470136653665]
  We evaluate the robustness and expressiveness of value representations across three widely used probing strategies.<n>We show that the demographic context has little effect on the free-text generation, and the models' values only weakly correlate with their preference for value-based actions.
  arXiv  Detail & Related papers  (2025-07-17T18:56:41Z)
• Can Generated Images Serve as a Viable Modality for Text-Centric Multimodal Learning? [3.966028515034415]
  This work systematically investigates whether images generated on-the-fly by Text-to-Image (T2I) models can serve as a valuable complementary modality for text-centric tasks.
  arXiv  Detail & Related papers  (2025-06-21T07:32:09Z)
• Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity [27.898678946802438]
  We introduce a novel data-driven approach for interpreting granular ratings in pluralistic datasets.<n>We distill non-parametric responsiveness metrics that quantify the consistency of raters in scoring varying levels of the severity of safety violations.<n>We show that our approach can inform rater selection and feedback interpretation by capturing nuanced viewpoints across different demographic groups.
  arXiv  Detail & Related papers  (2025-03-07T17:32:31Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups [29.720095331989064]
  AI systems crucially rely on human ratings, but these ratings are often aggregated. This is particularly concerning when evaluating the safety of generative AI, where perceptions and associated harms can vary significantly across socio-cultural contexts. We conduct a large-scale study employing highly-parallel safety ratings of about 1000 text-to-image (T2I) generations from a demographically diverse rater pool of 630 raters.
  arXiv  Detail & Related papers  (2024-10-22T13:59:21Z)
• PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification [73.64560354556498]
  Vision Transformer (ViT) tends to overfit on most distinct regions of training data, limiting its generalizability and attention to holistic object features. We present PartFormer, an innovative adaptation of ViT designed to overcome the limitations in object Re-ID tasks. Our framework significantly outperforms state-of-the-art by 2.4% mAP scores on the most challenging MSMT17 dataset.
  arXiv  Detail & Related papers  (2024-08-29T16:31:05Z)
• Separating common from salient patterns with Contrastive Representation Learning [2.250968907999846]
  Contrastive Analysis aims at separating common factors of variation between two datasets. Current models based on Variational Auto-Encoders have shown poor performance in learning semantically-expressive representations. We propose to leverage the ability of Contrastive Learning to learn semantically expressive representations well adapted for Contrastive Analysis.
  arXiv  Detail & Related papers  (2024-02-19T08:17:13Z)
• Stable Bias: Analyzing Societal Representations in Diffusion Models [72.27121528451528]
  We propose a new method for exploring the social biases in Text-to-Image (TTI) systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts. We leverage this method to analyze images generated by 3 popular TTI systems and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents.
  arXiv  Detail & Related papers  (2023-03-20T19:32:49Z)
• Variational Distillation for Multi-View Learning [104.17551354374821]
  We design several variational information bottlenecks to exploit two key characteristics for multi-view representation learning. Under rigorously theoretical guarantee, our approach enables IB to grasp the intrinsic correlation between observations and semantic labels.
  arXiv  Detail & Related papers  (2022-06-20T03:09:46Z)
• Assessing Demographic Bias Transfer from Dataset to Model: A Case Study in Facial Expression Recognition [1.5340540198612824]
  Two metrics focus on the representational and stereotypical bias of the dataset, and the third one on the residual bias of the trained model. We demonstrate the usefulness of the metrics by applying them to a FER problem based on the popular Affectnet dataset.
  arXiv  Detail & Related papers  (2022-05-20T09:40:42Z)
• Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction [71.97877759413272]
  Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Recent methods have achieved strong performances using Multi-Choice Learning objectives like winner-takes-all (WTA) or best-of-many. Our work addresses two key challenges in trajectory prediction, learning outputs, and better predictions by imposing constraints using driving knowledge.
  arXiv  Detail & Related papers  (2021-04-16T17:58:56Z)

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.