# Are Language Models Consequentialist or Deontological Moral Reasoners?

arXiv: https://arxiv.org/abs/2505.21479 · HTML: https://mlsanity.com/paper/2505.21479/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 15 of its 56 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [2 OLMo 2 Furious](https://mlsanity.com/paper/2501.00656/) (2024)
- [Evaluation of OpenAI o1: Opportunities and Challenges of AGI](https://mlsanity.com/paper/2409.18486/) (2024)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models](https://mlsanity.com/paper/2312.06281/) (2023)
- [Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs](https://mlsanity.com/paper/2502.08640/) (2025)
- [MoralBench: Moral Evaluation of LLMs](https://mlsanity.com/paper/2406.04428/) (2024)
- [Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models](https://mlsanity.com/paper/2411.12580/) (2024)
- [Probing the Moral Development of Large Language Models through Defining Issues Test](https://mlsanity.com/paper/2309.13356/) (2023)
- [Large-scale moral machine experiment on large language models](https://mlsanity.com/paper/2411.06790/) (2024)

## Built on by (most cited first, 12 of 12)

- [MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes](https://mlsanity.com/paper/2510.16380/) (2025)
- [ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs](https://mlsanity.com/paper/2510.00857/) (2025)
- [Can Revealed Preferences Clarify LLM Alignment and Steering?](https://mlsanity.com/paper/2605.08556/) (2026)
- [Evaluating Cooperation in LLM Social Groups through Elected Leadership](https://mlsanity.com/paper/2604.11721/) (2026)
- [Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph](https://mlsanity.com/paper/2603.15527/) (2026)
- [Measuring Moral LLM Responses in Multilingual Capacities](https://mlsanity.com/paper/2510.08776/) (2025)
- [Reinforcing privacy reasoning in LLMs via normative simulacra from fiction](https://mlsanity.com/paper/2604.20904/) (2026)
- [Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations](https://mlsanity.com/paper/2606.05890/) (2026)
- [Are LLMs Bad at Moral Reasoning?](https://mlsanity.com/paper/2606.11635/) (2026)
- [MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning](https://mlsanity.com/paper/2607.11736/) (2026)
- [Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture](https://mlsanity.com/paper/2608.14566/) (2026)
- [Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking](https://mlsanity.com/paper/2609.14998/) (2026)

## Abstract (arXiv)

As AI systems increasingly navigate applications in healthcare, law, and governance, understanding how they handle ethically complex scenarios becomes critical. Previous work has mainly examined the moral judgments in large language models (LLMs), rather than their underlying moral reasoning process. In contrast, we focus on a large-scale analysis of the moral reasoning traces provided by LLMs. Furthermore, unlike prior work that attempted to draw inferences from only a handful of moral dilemmas, our study leverages over 600 distinct trolley problems as probes for revealing the reasoning patterns that emerge within different LLMs. We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology. Our analysis reveals that LLM chains-of-thought tend to favor deontological principles based on moral obligations, while post-hoc explanations shift notably toward consequentialist rationales that emphasize utility. Our framework provides a foundation for understanding how LLMs process and articulate ethical considerations, an important step toward safe and interpretable deployment of LLMs in high-stakes decision-making environments. Our code is available at https://github.com/keenansamway/moral-lens .