# The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis

arXiv: https://arxiv.org/abs/2509.10297 · HTML: https://mlsanity.com/paper/2509.10297/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour](https://mlsanity.com/paper/2311.09410/) (2023)
- [Hybrid Intelligence](https://mlsanity.com/paper/2105.00691/) (2021)
- [Cooperating with Machines](https://mlsanity.com/paper/1703.06207/) (2017)
- [Ironies of Generative AI: Understanding and mitigating productivity loss in human-AI interactions](https://mlsanity.com/paper/2402.11364/) (2024)
- [Value alignment: a formal approach](https://mlsanity.com/paper/2110.09240/) (2021)
- [Human-AI Symbiosis: A Survey of Current Approaches](https://mlsanity.com/paper/2103.09990/) (2021)
- [Heuristic Reasoning in AI: Instrumental Use and Mimetic Absorption](https://mlsanity.com/paper/2403.09404/) (2024)
- [Super Co-alignment of Human and AI for Sustainable Symbiotic Society](https://mlsanity.com/paper/2504.17404/) (2025)

## Built on by (most cited first, 1 of 1)

- [Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability](https://mlsanity.com/paper/2510.12229/) (2025)

## Abstract (arXiv)

Artificial intelligence (AI) is advancing at a pace that raises urgent questions about how to align machine decision-making with human moral values. This working paper investigates how leading AI systems prioritize moral outcomes and what this reveals about the prospects for human-AI symbiosis. We address two central questions: (1) What moral values do state-of-the-art large language models (LLMs) implicitly favour when confronted with dilemmas? (2) How do differences in model architecture, cultural origin, and explainability affect these moral preferences? To explore these questions, we conduct a quantitative experiment with six LLMs, ranking and scoring outcomes across 18 dilemmas representing five moral frameworks. Our findings uncover strikingly consistent value biases. Across all models, Care and Virtue values outcomes were rated most moral, while libertarian choices were consistently penalized. Reasoning-enabled models exhibited greater sensitivity to context and provided richer explanations, whereas non-reasoning models produced more uniform but opaque judgments. This research makes three contributions: (i) Empirically, it delivers a large-scale comparison of moral reasoning across culturally distinct LLMs; (ii) Theoretically, it links probabilistic model behaviour with underlying value encodings; (iii) Practically, it highlights the need for explainability and cultural awareness as critical design principles to guide AI toward a transparent, aligned, and symbiotic future.