Foundational Moral Values for AI Alignment
Not on the map. Why?
Abstract (arXiv)
Solving the AI alignment problem requires having clear, defensible values towards which AI systems can align. Currently, targets for alignment remain underspecified and do not seem to be built from a philosophically robust structure. We begin the discussion of this problem by presenting five core, foundational values, drawn from moral philosophy and built on the requisites for human existence: survival, sustainable intergenerational existence, society, education, and truth. We show that these values not only provide a clearer direction for technical alignment work, but also serve as a framework to highlight threats and opportunities from AI systems to both obtain and sustain these values.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 64 references that are in the map. First posted on arXiv 28 Nov 2023.
Builds on
20 of 64 references.
References · 20
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2016Concrete Problems in AI Safetycited by 1,582
- 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
- 2020Aligning AI With Shared Human Valuescited by 706
- 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
- 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
- 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
- 2020Artificial Intelligence, Values and Alignmentcited by 443
- 2018Scalable agent alignment via reward modeling: a research directioncited by 438
- 2021Alignment of Language Agentscited by 167
8 more
- 2023Auditing large language models: a three-layered approachcited by 135
- 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
- 2023Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writerscited by 32
- 2020Combating Disinformation in a Social Media Agecited by 17
- 2023The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Modelscited by 7
- 2023A Multi-Level Framework for the AI Alignment Problemcited by 5
- 2019ML for Flood Forecasting at Scalecited by 3
- 2023A multilevel framework for AI governancecited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.