mlsanityData to 7 Oct 2026

Probing the Moral Development of Large Language Models through Defining Issues Test

arXiv 2309.13356 ↗First posted 23 Sep 2023cs.CL cs.AIcited by 23

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

In this study, we measure the moral reasoning ability of LLMs using the Defining Issues Test - a psychometric instrument developed for measuring the moral development stage of a person according to the Kohlberg's Cognitive Moral Development Model. DIT uses moral dilemmas followed by a set of ethical considerations that the respondent has to judge for importance in resolving the dilemma, and then rank-order them by importance. A moral development stage score of the respondent is then computed based on the relevance rating and ranking. Our study shows that early LLMs such as GPT-3 exhibit a moral reasoning ability no better than that of a random baseline, while ChatGPT, Llama2-Chat, PaLM-2 and GPT-4 show significantly better performance on this task, comparable to adult humans. GPT-4, in fact, has the highest post-conventional moral reasoning score, equivalent to that of typical graduate school students. However, we also observe that the models do not perform consistently across all dilemmas, pointing to important gaps in their understanding and reasoning abilities.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 25 of its 56 references that are in the map. First posted on arXiv 23 Sep 2023.

Builds on

25 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?29 Aug
  2. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity8 Feb

Other references · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  5. 2021Ethical and social risks of harm from Language Modelscited by 957
  6. 2020Aligning AI With Shared Human Valuescited by 706
  7. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  8. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  9. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  10. 2023How is ChatGPT's behavior changing over time?cited by 265
  11. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  12. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
11 more
  1. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 168
  2. 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
  3. 2020Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequencescited by 133
  4. 2023ProPILE: Probing Privacy Leakage in Large Language Modelscited by 127
  5. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  6. 2020Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotescited by 100
  7. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  8. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 90
  9. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Modelscited by 45
  10. 2019Suicidal Ideation Detection: A Review of Machine Learning Methods and Applicationscited by 31
  11. 2019BERT has a Moral Compass: Improvements of ethical and moral values of machinescited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 11; 2026: 5.

23 papers.

Sort:

By area:

  1. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  2. 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoningcited by 91
  3. 2025The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Processcited by 21
  4. 2026Large Language Model Reasoning Failurescited by 20
  5. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  6. 2024Exploring and steering the moral compass of Large Language Modelscited by 15
  7. 2025Are Language Models Consequentialist or Deontological Moral Reasoners?cited by 12
  8. 2024Evaluating Moral Beliefs across LLMs through a Pluralistic Frameworkcited by 11
  9. 2025Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMscited by 10
  10. 2024Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Testcited by 9
  11. 2025Meta-Cultural Competence: Climbing the Right Hill of Cultural Awarenesscited by 8
  12. 2025Societal Alignment Frameworks Can Improve LLM Alignmentcited by 8
11 more
  1. 2025Auditing the Ethical Logic of Generative AI Modelscited by 5
  2. 2025RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivitycited by 4
  3. 2024Eagle: Ethical Dataset Given from Real Interactionscited by 3
  4. 2024Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communitiescited by 2
  5. 2025User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMscited by 2
  6. 2025Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Taskscited by 1
  7. 2026When Do Language Models Endorse Limitations on Human Rights Principles?cited by 1
  8. 2026Conflicts Make Large Reasoning Models Vulnerable to Attackscited by 1
  9. 2025Bridging AI and Carbon Capture: A Dataset for LLMs in Ionic Liquids and CBE Researchcited by 0
  10. 2026Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challengescited by 0
  11. 2026The Evolutionary Origin of Values: implications for AI alignment, sentience and existential riskcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
  2. 2025Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework
  3. 2023Potential Benefits of Employing Large Language Models in Research in Moral Education and Development
  4. 2025Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
  5. 2023Exploring the psychology of LLMs' Moral and Legal Reasoning
  6. 2025"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
  7. 2024MoralBench: Moral Evaluation of LLMs
  8. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in