mlsanityData to 14 Oct 2026

MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations Theory

arXiv 2506.05696 ↗First posted 6 Jun 2025cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Recent advances in vision-language models have enabled rich semantic understanding across modalities. However, these encoding methods lack the ability to interpret or reason about the moral dimensions of content-a crucial aspect of human cognition. In this paper, we address this gap by introducing MoralCLIP, a novel embedding representation method that extends multimodal learning with explicit moral grounding based on Moral Foundations Theory (MFT). Our approach integrates visual and textual moral cues into a unified embedding space, enabling cross-modal moral alignment. MoralCLIP is grounded on the multi-label dataset Social-Moral Image Database to identify co-occurring moral foundations in visual content. For MoralCLIP training, we design a moral data augmentation strategy to scale our annotated dataset to 15,000 image-text pairs labeled with MFT-aligned dimensions. Our results demonstrate that explicit moral supervision improves both unimodal and multimodal understanding of moral content, establishing a foundation for morally-aware AI systems capable of recognizing and aligning with human moral values.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 28 of its 74 references that are in the map. First posted on arXiv 6 Jun 2025.

Builds on

28 of 74 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models30 Dec
  2. 2024PaliGemma: A versatile 3B VLM for transfer10 Jul
  3. 2024VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values3 Jul

Other references · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  8. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  9. 2020Aligning AI With Shared Human Valuescited by 723
  10. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 300
  11. 2017Sampling Matters in Deep Embedding Learningcited by 285
  12. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
13 more
  1. 2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
  2. 2022Image Retrieval from Contextual Descriptionscited by 26
  3. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Modelscited by 23
  4. 2024MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussionscited by 23
  5. 2023A Data Fusion Framework for Multi-Domain Morality Learningcited by 14
  6. 2023Measuring Moral Dimensions in Social Media with Mformercited by 13
  7. 2024Is CLIP the main roadblock for fine-grained open-world perception?cited by 13
  8. 2024Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encodercited by 11
  9. 2023MOKA: Moral Knowledge Augmentation for Moral Event Extractioncited by 7
  10. 2018Development and Validation of the Japanese Moral Foundations Dictionarycited by 6
  11. 2023Blind Dates: Examining the Expression of Temporality in Historical Photographscited by 5
  12. 2022Zero-shot Visual Commonsense Immorality Predictioncited by 2
  13. 2024E2MoCase: A Dataset for Emotional, Event and Moral Observations in News Articles on High-impact Legal Casescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise Alignment
  2. 2025MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
  3. 2026Tracing Moral Foundations in Large Language Models
  4. 2026Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
  5. 2026Visual Distraction Undermines Moral Reasoning in Vision-Language Models
  6. 2022Ensuring Visual Commonsense Morality for Text-to-Image Generation
  7. 2026Representational alignment yields generalizable safety in language models
  8. 2026Unsupervised Elicitation of Moral Values from Language Models