mlsanityData to 7 Oct 2026

Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions

arXiv 2604.21871 ↗First posted 23 Apr 2026cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We characterize machine behavior using the Whistleblower's Dilemma by varying two experimental dimensions: crime severity and relational closeness. Our study evaluates three distinct perspectives: (1) moral rightness (prescriptive norms), (2) predicted human behavior (descriptive social expectations), and (3) autonomous model decision-making. By analyzing the reasoning processes, we identify a clear cross-perspective divergence: while moral rightness remains consistently fairness-oriented, predicted human behavior shifts significantly toward loyalty as relational closeness increases. Crucially, model decisions align with moral rightness judgments rather than their own behavioral predictions. This inconsistency suggests that LLM decision-making prioritizes rigid, prescriptive rules over the social sensitivity present in their internal world-modeling, which poses a gap that may lead to significant misalignments in real-world deployments.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 6 of its 31 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

6 of 31 references.

References · 6

  1. 2024Language Model Alignment in Multilingual Trolley Problemscited by 46
  2. 2023Measuring Moral Dimensions in Social Media with Mformercited by 13
  3. 2023Decolonial AI Alignment: Openness, Vi'sedsa-Dharma, and Including Excluded Knowledgescited by 10
  4. 2025Exploring Persona-dependent LLM Alignment for the Moral Machine Experimentcited by 9
  5. 2024A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptivecited by 8
  6. 2026Moral Outrage Shapes Commitments Beyond Attention: Multimodal Moral Emotions on YouTube in Korea and the UScited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevancecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
  2. 2025The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  3. 2023Exploring the psychology of LLMs' Moral and Legal Reasoning
  4. 2026Why AI Alignment Failure Is Structural: Learned Human Interaction Structures and AGI as an Endogenous Evolutionary Shock
  5. 2024The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making
  6. 2025Many LLMs Are More Utilitarian Than One
  7. 2025Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment
  8. 2026Scaling Laws for Moral Machine Judgment in Large Language Models