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

• URL: http://arxiv.org/abs/2506.05696v1
• Date: Fri, 06 Jun 2025 02:52:13 GMT
• Title: MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations Theory
• Authors: Ana Carolina Condez, Diogo Tavares, João Magalhães,
• Abstract summary: MoralCLIP is a novel embedding representation method that extends multimodal learning with explicit moral grounding.<n>MoralCLIP is grounded on the multi-label dataset Social-Moral Image Database to identify co-occurring moral foundations in visual content.<n>Our results demonstrate that explicit moral supervision improves both unimodal and multimodal understanding of moral content.
• Score: 8.486534745997396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Are Language Models Consequentialist or Deontological Moral Reasoners? [69.85385952436044]
  We focus on a large-scale analysis of the moral reasoning traces provided by large language models (LLMs)<n>We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology.
  arXiv  Detail & Related papers  (2025-05-27T17:51:18Z)
• MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models [38.0475868976819]
  Vision-language models have demonstrated increasing influence in morally sensitive domains such as autonomous driving and medical analysis.<n>We introduce MORALISE, a benchmark for evaluating the moral alignment of vision-language models using diverse, expert-verified real-world data.
  arXiv  Detail & Related papers  (2025-05-20T01:11:17Z)
• M$^3$oralBench: A MultiModal Moral Benchmark for LVLMs [66.78407469042642]
  We introduce M$3$oralBench, the first MultiModal Moral Benchmark for LVLMs.<n>M$3$oralBench expands the everyday moral scenarios in Moral Foundations Vignettes (MFVs) and employs the text-to-image diffusion model, SD3.0, to create corresponding scenario images.<n>It conducts moral evaluation across six moral foundations of Moral Foundations Theory (MFT) and encompasses tasks in moral judgement, moral classification, and moral response.
  arXiv  Detail & Related papers  (2024-12-30T05:18:55Z)
• Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning [4.925187725973777]
  Pluralist moral philosophers argue that human morality can be deconstructed into a finite number of elements. We build a pluralist moral sentence embedding space via a state-of-the-art contrastive learning approach. Our results show that a pluralist approach to morality can be captured in an embedding space.
  arXiv  Detail & Related papers  (2024-01-30T18:15:25Z)
• What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations [48.686872351114964]
  Moral or ethical judgments rely heavily on the specific contexts in which they occur. We introduce defeasible moral reasoning: a task to provide grounded contexts that make an action more or less morally acceptable. We distill a high-quality dataset of 1.2M entries of contextualizations and rationales for 115K defeasible moral actions.
  arXiv  Detail & Related papers  (2023-10-24T00:51:29Z)
• Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? [78.3738172874685]
  Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research.
  arXiv  Detail & Related papers  (2023-08-29T15:57:32Z)
• MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions [71.25236662907056]
  A moral dialogue system aligned with users' values could enhance conversation engagement and user connections. We propose a framework, MoralDial, to train and evaluate moral dialogue systems.
  arXiv  Detail & Related papers  (2022-12-21T02:21:37Z)
• Identifying Morality Frames in Political Tweets using Relational Learning [27.047907641503762]
  Moral sentiment is motivated by its targets, which can correspond to individuals or collective entities. We introduce morality frames, a representation framework for organizing moral attitudes directed at different entities. We propose a relational learning model to predict moral attitudes towards entities and moral foundations jointly.
  arXiv  Detail & Related papers  (2021-09-09T19:48:57Z)
• Aligning AI With Shared Human Values [85.2824609130584]
  We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. We find that current language models have a promising but incomplete ability to predict basic human ethical judgements. Our work shows that progress can be made on machine ethics today, and it provides a steppingstone toward AI that is aligned with human values.
  arXiv  Detail & Related papers  (2020-08-05T17:59:16Z)
• Text-based inference of moral sentiment change [11.188112005462536]
  We present a text-based framework for investigating moral sentiment change of the public via longitudinal corpora. We build our methodology by exploring moral biases learned from diachronic word embeddings. Our work offers opportunities for applying natural language processing toward characterizing moral sentiment change in society.
  arXiv  Detail & Related papers  (2020-01-20T18:52:45Z)

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.