# Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment

arXiv: https://arxiv.org/abs/2504.10886 · HTML: https://mlsanity.com/paper/2504.10886/

## 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.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [Language Model Alignment in Multilingual Trolley Problems](https://mlsanity.com/paper/2407.02273/) (2024)
- [The Moral Machine Experiment on Large Language Models](https://mlsanity.com/paper/2309.05958/) (2023)
- [Large-scale moral machine experiment on large language models](https://mlsanity.com/paper/2411.06790/) (2024)
- [Moral Dilemmas for Moral Machines](https://mlsanity.com/paper/2203.06152/) (2022)

## Built on by (most cited first, 9 of 9)

- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity](https://mlsanity.com/paper/2509.25897/) (2025)
- [Localizing Persona Representations in LLMs](https://mlsanity.com/paper/2505.24539/) (2025)
- [Street-Level AI: Are Large Language Models Ready for Real-World Judgments?](https://mlsanity.com/paper/2508.08193/) (2025)
- [Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona?](https://mlsanity.com/paper/2508.03262/) (2025)
- [Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment](https://mlsanity.com/paper/2511.13290/) (2025)
- [Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions](https://mlsanity.com/paper/2604.21871/) (2026)
- [Demographic Biases and Gaps in the Perception of Sexism in Large Language Models](https://mlsanity.com/paper/2508.18245/) (2025)
- [Training-Free Cultural Alignment of Large Language Models via Persona Disagreement](https://mlsanity.com/paper/2605.10843/) (2026)

## 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.