Toward a Theory of Value in AI Alignment

• URL: http://arxiv.org/abs/2608.10327v1
• Date: Mon, 10 Aug 2026 23:57:02 GMT
• Title: Toward a Theory of Value in AI Alignment
• Abstract summary: The popularization of large language models has seen a rise in harms spanning from toxic speech and hallucinations to AI agents executing unauthorized actions.<n>Within the field of AI safety, these harmful instances are often framed as the alignment problem, or of models being misaligned with human values.<n>How does the field of AI value alignment conceive of human values?<n>We annotated 94 value alignment research papers to discern their implicit theory of values in AI.
• Score: 8.20706299979115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can AI systems be aligned to human values? The popularization of large language models (LLMs) and multi-modal foundation models has seen a rise in harms spanning from toxic speech and hallucinations to AI agents executing unauthorized actions. Within the field of AI safety, these harmful instances are often framed as the alignment problem, or of models being misaligned with human values. Researchers have responded by pursuing applied and theoretical AI value alignment efforts, often without specifying what they mean by human values. How does the field of AI value alignment conceive of human values? How are these conceptions of values technically operationalized and evaluated? What does the emergent theory of value from this field signify for the future of AI? We annotated 94 value alignment research papers to discern their implicit theory of values in AI. The majority do not define values, relying heavily on preferences as a stand in that runs the risk of reducing complex culturally situated concepts down to binary choices. As researchers dispense with using human annotators for model training and evaluation, turning instead to synthetic data and autorater approaches to aligning and evaluating models, we identify the potential to close off alternative methods for contesting and enacting values in foundation models. In making AI value alignments philosophical commitments explicit, we seek to bring great specificity and under explored perspectives in the debate on whether and how AI can address human values.

Related papers

• AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations [9.253070075439746]
  13 participants left our study convinced that AI can understand human values.<n>We warn about "weaponized empathy": a potentially dangerous design pattern that may arise in value-aligned, yet welfare-misaligned AI.
  arXiv  Detail & Related papers  (2026-01-30T01:19:54Z)
• Rethinking How AI Embeds and Adapts to Human Values: Challenges and Opportunities [0.6113558800822273]
  We argue that AI systems should implement long-term reasoning and remain adaptable to evolving values.<n>Value alignment requires more theories to address the full spectrum of human values.<n>We identify the challenges associated with value alignment and indicate directions for advancing value alignment research.
  arXiv  Detail & Related papers  (2025-08-23T18:19:05Z)
• Modeling Human Beliefs about AI Behavior for Scalable Oversight [16.068386375496086]
  We propose modeling evaluators' beliefs to interpret their feedback more reliably.<n>We formalize human belief models, analyze their theoretical role in value learning, and characterize when ambiguity remains.<n>These representations could be used to learn correct values from human feedback even when evaluators misunderstand the AI's behavior.
  arXiv  Detail & Related papers  (2025-02-28T17:39:55Z)
• ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs [16.711615737109977]
  We introduce Value, a framework of fundamental values, grounded in psychological theory and a systematic review.<n>We apply Value to measure the value alignment of humans and large language models (LLMs) across four real-world scenarios.
  arXiv  Detail & Related papers  (2024-09-15T02:13:03Z)
• Modelling Human Values for AI Reasoning [2.320648715016106]
  We detail a formal model of human values for their explicit computational representation. We show how this model can provide the foundational apparatus for AI-based reasoning over values. We propose a roadmap for future integrated, and interdisciplinary, research into human values in AI.
  arXiv  Detail & Related papers  (2024-02-09T12:08:49Z)
• Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties [68.66719970507273]
  Value pluralism is the view that multiple correct values may be held in tension with one another. As statistical learners, AI systems fit to averages by default, washing out potentially irreducible value conflicts. We introduce ValuePrism, a large-scale dataset of 218k values, rights, and duties connected to 31k human-written situations.
  arXiv  Detail & Related papers  (2023-09-02T01:24:59Z)
• Fairness in AI and Its Long-Term Implications on Society [68.8204255655161]
  We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time. We discuss how biased models can lead to more negative real-world outcomes for certain groups. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest.
  arXiv  Detail & Related papers  (2023-04-16T11:22:59Z)
• Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap [56.611702960809644]
  We benchmark AI's ability to imitate humans in three language tasks and three vision tasks.<n>Next, we conducted 72,191 Turing-like tests with 1,916 human judges and 10 AI judges.<n>Imitation ability showed minimal correlation with conventional AI performance metrics.
  arXiv  Detail & Related papers  (2022-11-23T16:16:52Z)
• Metaethical Perspectives on 'Benchmarking' AI Ethics [81.65697003067841]
  Benchmarks are seen as the cornerstone for measuring technical progress in Artificial Intelligence (AI) research. An increasingly prominent research area in AI is ethics, which currently has no set of benchmarks nor commonly accepted way for measuring the 'ethicality' of an AI system. We argue that it makes more sense to talk about 'values' rather than 'ethics' when considering the possible actions of present and future AI systems.
  arXiv  Detail & Related papers  (2022-04-11T14:36:39Z)
• Trustworthy AI: A Computational Perspective [54.80482955088197]
  We focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems.
  arXiv  Detail & Related papers  (2021-07-12T14:21:46Z)
• 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)

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.