mlsanityData to 14 Oct 2026

Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment

arXiv 2504.10886 ↗First posted 15 Apr 2025cs.CY cs.AI cs.CLcited by 9

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Deploying large language models (LLMs) with agency in real-world applications raises critical questions about how these models will behave. In particular, how will their decisions align with humans when faced with moral dilemmas? This study examines the alignment between LLM-driven decisions and human judgment in various contexts of the moral machine experiment, including personas reflecting different sociodemographics. We find that the moral decisions of LLMs vary substantially by persona, showing greater shifts in moral decisions for critical tasks than humans. Our data also indicate an interesting partisan sorting phenomenon, where political persona predominates the direction and degree of LLM decisions. We discuss the ethical implications and risks associated with deploying these models in applications that involve moral decisions.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 15 of its 20 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

15 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Language Model Alignment in Multilingual Trolley Problems2 Jul

Other references · 14

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  6. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  7. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 199
  8. 2023Large Language Models for Robotics: A Surveycited by 133
  9. 2023PALR: Personalization Aware LLMs for Recommendationcited by 96
  10. 2023Moral Foundations of Large Language Modelscited by 85
  11. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 74
  12. 2023The Moral Machine Experiment on Large Language Modelscited by 25
2 more
  1. 2024Large-scale moral machine experiment on large language modelscited by 9
  2. 2022Moral Dilemmas for Moral Machinescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 2.

9 papers.

  1. 2025Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamicscited by 19
  2. 2025RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivitycited by 4
  3. 2025Localizing Persona Representations in LLMscited by 3
  4. 2025Street-Level AI: Are Large Language Models Ready for Real-World Judgments?cited by 3
  5. 2025Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona?cited by 2
  6. 2025Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignmentcited by 2
  7. 2026Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisionscited by 1
  8. 2025Demographic Biases and Gaps in the Perception of Sexism in Large Language Modelscited by 0
  9. 2026Training-Free Cultural Alignment of Large Language Models via Persona Disagreementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making
  2. 2023Exploring the psychology of LLMs' Moral and Legal Reasoning
  3. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants
  4. 2024Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations
  5. 2024Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
  6. 2025The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  7. 2025Normative Evaluation of Large Language Models with Everyday Moral Dilemmas
  8. 2025From Stability to Inconsistency: A Study of Moral Preferences in LLMs