# Evaluating Moral Beliefs across LLMs through a Pluralistic Framework arXiv: https://arxiv.org/abs/2411.03665 ยท HTML: https://mlsanity.com/paper/2411.03665/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 22 of its 48 references that are in the map. - First posted on arXiv 6 Nov 2024. ## Builds on (most cited first, 22 of 22) - [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023) - [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021) - [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021) - [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023) - [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020) - [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024) - [Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties](https://mlsanity.com/paper/2309.00779/) (2023) - [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023) - [NormBank: A Knowledge Bank of Situational Social Norms](https://mlsanity.com/paper/2305.17008/) (2023) - [Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate](https://mlsanity.com/paper/2402.07401/) (2024) - [Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate](https://mlsanity.com/paper/2401.16788/) (2024) - [ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations](https://mlsanity.com/paper/2212.10409/) (2022) - [Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates](https://mlsanity.com/paper/2312.06861/) (2023) - [Probing the Moral Development of Large Language Models through Defining Issues Test](https://mlsanity.com/paper/2309.13356/) (2023) - [MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions](https://mlsanity.com/paper/2212.10720/) (2022) - [What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations](https://mlsanity.com/paper/2310.15431/) (2023) - [Do Differences in Values Influence Disagreements in Online Discussions?](https://mlsanity.com/paper/2310.15757/) (2023) - [Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values](https://mlsanity.com/paper/2210.07652/) (2022) - [Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test](https://mlsanity.com/paper/2402.02135/) (2024) - [Opening up Minds with Argumentative Dialogues](https://mlsanity.com/paper/2301.06400/) (2023) - [Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning](https://mlsanity.com/paper/2401.17228/) (2024) - [Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning](https://mlsanity.com/paper/2312.17479/) (2023) ## Built on by (most cited first, 11 of 11) - [VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare](https://mlsanity.com/paper/2502.13775/) (2025) - [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025) - [Made-in China, Thinking in America:U.S. Values Persist in Chinese LLMs](https://mlsanity.com/paper/2512.13723/) (2025) - [C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models](https://mlsanity.com/paper/2506.01495/) (2025) - [Exploring Cultural Variations in Moral Judgments with Large Language Models](https://mlsanity.com/paper/2506.12433/) (2025) - [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026) - [Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgment](https://mlsanity.com/paper/2606.14037/) (2026) - [The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment](https://mlsanity.com/paper/2607.05552/) (2026) - [EMNLP: Educator-role Moral and Normative Large Language Models Profiling](https://mlsanity.com/paper/2508.15250/) (2025) - [A Roadmap to Impactful Pluralistic Alignment Research](https://mlsanity.com/paper/2607.22305/) (2026) - [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026) ## Abstract (arXiv) Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral choice scenarios in Chinese, derived from moral words. The decision-making process of the models in these scenarios reveals their moral principle preferences. By ranking these moral choices, we discern the varying moral beliefs held by different language models. Additionally, through moral debates, we investigate the firmness of these models to their moral choices. Our findings indicate that English language models, namely ChatGPT and Gemini, closely mirror moral decisions of the sample of Chinese university students, demonstrating strong adherence to their choices and a preference for individualistic moral beliefs. In contrast, Chinese models such as Ernie and ChatGLM lean towards collectivist moral beliefs, exhibiting ambiguity in their moral choices and debates. This study also uncovers gender bias embedded within the moral beliefs of all examined language models. Our methodology offers an innovative means to assess moral beliefs in both artificial and human intelligence, facilitating a comparison of moral values across different cultures.