mlsanityData to 14 Oct 2026

Towards ethical multimodal systems

arXiv 2304.13765 ↗First posted 26 Apr 2023cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Generative AI systems (ChatGPT, DALL-E, etc) are expanding into multiple areas of our lives, from art Rombach et al. [2021] to mental health Rob Morris and Kareem Kouddous [2022]; their rapidly growing societal impact opens new opportunities, but also raises ethical concerns. The emerging field of AI alignment aims to make AI systems reflect human values. This paper focuses on evaluating the ethics of multimodal AI systems involving both text and images - a relatively under-explored area, as most alignment work is currently focused on language models. We first create a multimodal ethical database from human feedback on ethicality. Then, using this database, we develop algorithms, including a RoBERTa-large classifier and a multilayer perceptron, to automatically assess the ethicality of system responses.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 44 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

16 of 44 references.

References · 16

  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. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  8. 2016Concrete Problems in AI Safetycited by 1,642
  9. 2020Aligning AI With Shared Human Valuescited by 723
  10. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  11. 2021Unsolved Problems in ML Safetycited by 292
  12. 2021MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuningcited by 85
4 more
  1. 2015Towards Universal Paraphrastic Sentence Embeddingscited by 60
  2. 2021fairadapt: Causal Reasoning for Fair Data Pre-processingcited by 16
  3. 2021CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classificationcited by 16
  4. 2022Aligning MAGMA by Few-Shot Learning and Finetuningcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Multimodal Alignment and Fusion: A Surveycited by 74