mlsanityData to 7 Oct 2026

Exploring the psychology of LLMs' Moral and Legal Reasoning

arXiv 2308.01264 ↗First posted 2 Aug 2023cs.AI cs.CLcited by 43

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large language models (LLMs) exhibit expert-level performance in tasks across a wide range of different domains. Ethical issues raised by LLMs and the need to align future versions makes it important to know how state of the art models reason about moral and legal issues. In this paper, we employ the methods of experimental psychology to probe into this question. We replicate eight studies from the experimental literature with instances of Google's Gemini Pro, Anthropic's Claude 2.1, OpenAI's GPT-4, and Meta's Llama 2 Chat 70b. We find that alignment with human responses shifts from one experiment to another, and that models differ amongst themselves as to their overall alignment, with GPT-4 taking a clear lead over all other models we tested. Nonetheless, even when LLM-generated responses are highly correlated to human responses, there are still systematic differences, with a tendency for models to exaggerate effects that are present among humans, in part by reducing variance. This recommends caution with regards to proposals of replacing human participants with current state-of-the-art LLMs in psychological research and highlights the need for further research about the distinctive aspects of machine psychology.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 1 of its 47 references that are in the map. First posted on arXiv 2 Aug 2023.

Builds on

1 of 47 references.

References · 1

  1. 2020Artificial Intelligence, Values and Alignmentcited by 443

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 15; 2025: 16; 2026: 8.

43 papers.

Sort:

By area:

  1. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 125
  2. 2024Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligencecited by 65
  3. 2024MoralBench: Moral Evaluation of LLMscited by 50
  4. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  5. 2023Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMscited by 36
  6. 2023Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBenchcited by 28
  7. 2024Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Reviewcited by 17
  8. 2025Large Language Models Do Not Simulate Human Psychologycited by 17
  9. 2023AI Text-to-Behavior: A Study In Steerabilitycited by 11
  10. 2024Preemptive Detection and Correction of Misaligned Actions in LLM Agentscited by 9
  11. 2025Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Moralitycited by 9
  12. 2024In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Modelscited by 8
31 more
  1. 2025OntoTune: Ontology-Driven Self-training for Aligning Large Language Modelscited by 8
  2. 2025SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabiacited by 8
  3. 2025Many LLMs Are More Utilitarian Than Onecited by 7
  4. 2024Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approachcited by 6
  5. 2024Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspectivecited by 5
  6. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  7. 2025Comparing Moral Values in Western English-speaking societies and LLMs with Word Associationscited by 5
  8. 2024Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Modelscited by 4
  9. 2024Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemiacited by 4
  10. 2024SocialGaze: Improving the Integration of Human Social Norms in Large Language Modelscited by 4
  11. 2024Analyzing Nobel Prize Literature with Large Language Modelscited by 4
  12. 2024Investigating Context Effects in Similarity Judgements in Large Language Modelscited by 3
  13. 2024Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Frameworkcited by 3
  14. 2025When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governancecited by 3
  15. 2025Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theorycited by 3
  16. 2025Continual Pre-Training is (not) What You Need in Domain Adaptioncited by 2
  17. 2025Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Valuescited by 2
  18. 2025Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Modelscited by 2
  19. 2025The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledgecited by 2
  20. 2026The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisionscited by 2
  21. 2025PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theorycited by 1
  22. 2025Psychologically Enhanced AI Agentscited by 1
  23. 2026The conditional superiority of fast silicon samplingcited by 1
  24. 2024GPT-4's One-Dimensional Mapping of Morality: How the Accuracy of Country-Estimates Depends on Moral Domaincited by 0
  25. 2025Evidence of conceptual mastery in the application of rules by Large Language Modelscited by 0
  26. 2026How Human is AI? Examining the Impact of Emotional Prompts on Artificial and Human and Responsivenesscited by 0
  27. 2026Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Toolscited by 0
  28. 2026Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectivenesscited by 0
  29. 2026Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerabilitycited by 0
  30. 2026The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgmentcited by 0
  31. 2026Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogatescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making
  2. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants
  3. 2025Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
  4. 2024Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses
  5. 2024Language Model Alignment in Multilingual Trolley Problems
  6. 2025Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs
  7. 2026Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
  8. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications