# The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas

arXiv: https://arxiv.org/abs/2505.18154 · HTML: https://mlsanity.com/paper/2505.18154/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment](https://mlsanity.com/paper/2210.01478/) (2022)
- ['It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions](https://mlsanity.com/paper/1801.10408/) (2018)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life](https://mlsanity.com/paper/2410.02683/) (2024)
- [A Voting-Based System for Ethical Decision Making](https://mlsanity.com/paper/1709.06692/) (2017)
- [Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions](https://mlsanity.com/paper/2504.15236/) (2025)
- [Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values](https://mlsanity.com/paper/2311.10766/) (2023)
- [Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?](https://mlsanity.com/paper/2308.15399/) (2023)
- [Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning](https://mlsanity.com/paper/2310.11053/) (2023)
- [CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models](https://mlsanity.com/paper/2408.09819/) (2024)

## Built on by (most cited first, 13 of 13)

- [MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes](https://mlsanity.com/paper/2510.16380/) (2025)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [PRISON: Unmasking the Criminal Potential of Large Language Models](https://mlsanity.com/paper/2506.16150/) (2025)
- [Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability](https://mlsanity.com/paper/2603.16017/) (2026)
- [Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs](https://mlsanity.com/paper/2606.11232/) (2026)
- [Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis](https://mlsanity.com/paper/2511.17256/) (2025)
- [Morality in AI. A plea to embed morality in LLM architectures and frameworks](https://mlsanity.com/paper/2511.20689/) (2025)
- [Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs](https://mlsanity.com/paper/2601.08634/) (2026)
- [The Straight and Narrow: Do LLMs Possess an Internal Moral Path?](https://mlsanity.com/paper/2601.10307/) (2026)
- [Visual Distraction Undermines Moral Reasoning in Vision-Language Models](https://mlsanity.com/paper/2603.16445/) (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)
- [MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning](https://mlsanity.com/paper/2607.11736/) (2026)
- [TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback](https://mlsanity.com/paper/2608.28610/) (2026)

## Abstract (arXiv)

Ethical decision-making is a critical aspect of human judgment, and the growing use of LLMs in decision-support systems necessitates a rigorous evaluation of their moral reasoning capabilities. However, existing assessments primarily rely on single-step evaluations, failing to capture how models adapt to evolving ethical challenges. Addressing this gap, we introduce the Multi-step Moral Dilemmas (MMDs), the first dataset specifically constructed to evaluate the evolving moral judgments of LLMs across 3,302 five-stage dilemmas. This framework enables a fine-grained, dynamic analysis of how LLMs adjust their moral reasoning across escalating dilemmas. Our evaluation of nine widely used LLMs reveals that their value preferences shift significantly as dilemmas progress, indicating that models recalibrate moral judgments based on scenario complexity. Furthermore, pairwise value comparisons demonstrate that while LLMs often prioritize the value of care, this value can sometimes be superseded by fairness in certain contexts, highlighting the dynamic and context-dependent nature of LLM ethical reasoning. Our findings call for a shift toward dynamic, context-aware evaluation paradigms, paving the way for more human-aligned and value-sensitive development of LLMs.