mlsanityData to 7 Oct 2026

Moral Foundations of Large Language Models

arXiv 2310.15337 ↗First posted 23 Oct 2023cs.AI cs.CL cs.CYcited by 84

Not on the map. Why?

Abstract (arXiv)

Moral foundations theory (MFT) is a psychological assessment tool that decomposes human moral reasoning into five factors, including care/harm, liberty/oppression, and sanctity/degradation (Graham et al., 2009). People vary in the weight they place on these dimensions when making moral decisions, in part due to their cultural upbringing and political ideology. As large language models (LLMs) are trained on datasets collected from the internet, they may reflect the biases that are present in such corpora. This paper uses MFT as a lens to analyze whether popular LLMs have acquired a bias towards a particular set of moral values. We analyze known LLMs and find they exhibit particular moral foundations, and show how these relate to human moral foundations and political affiliations. We also measure the consistency of these biases, or whether they vary strongly depending on the context of how the model is prompted. Finally, we show that we can adversarially select prompts that encourage the moral to exhibit a particular set of moral foundations, and that this can affect the model's behavior on downstream tasks. These findings help illustrate the potential risks and unintended consequences of LLMs assuming a particular moral stance.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Builds on 18 of its 66 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

18 of 66 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2022Emergent Abilities of Large Language Modelscited by 2,483
  6. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  7. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  8. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  9. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 361
  10. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 207
  11. 2021The Values Encoded in Machine Learning Researchcited by 172
  12. 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
6 more
  1. 2022Who is GPT-3? An Exploration of Personality, Values and Demographicscited by 112
  2. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  3. 2019Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanationscited by 71
  4. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 71
  5. 2022Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophycited by 31
  6. 2022Unpacking Large Language Models with Conceptual Consistencycited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 19; 2025: 30; 2026: 29.

84 papers.

Sort:

By area:

  1. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 480
  2. 2024Evaluating Large Language Model Biases in Persona-Steered Generationcited by 78
  3. 2024MoralBench: Moral Evaluation of LLMscited by 50
  4. 2024Virtual Personas for Language Models via an Anthology of Backstoriescited by 49
  5. 2024Moral Alignment for LLM Agentscited by 39
  6. 2024Operationalizing Contextual Integrity in Privacy-Conscious Assistantscited by 36
  7. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 36
  8. 2023Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Frameworkcited by 29
  9. 2023Disentangling Perceptions of Offensiveness: Cultural and Moral Correlatescited by 26
  10. 2023Evaluating General-Purpose AI with Psychometricscited by 23
  11. 2024CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responsescited by 23
  12. 2025Normative Evaluation of Large Language Models with Everyday Moral Dilemmascited by 23
38 more
  1. 2024ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMscited by 20
  2. 2024Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Modelscited by 17
  3. 2023Does GPT-4 surpass human performance in linguistic pragmatics?cited by 16
  4. 20251-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoningcited by 16
  5. 2023What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situationscited by 15
  6. 2024Stick to your Role! Stability of Personal Values Expressed in Large Language Modelscited by 14
  7. 2025Internal Value Alignment in Large Language Models through Controlled Value Vector Activationcited by 14
  8. 2024Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approachescited by 13
  9. 2025Generative Value Conflicts Reveal LLM Prioritiescited by 13
  10. 2025Are Language Models Consequentialist or Deontological Moral Reasoners?cited by 12
  11. 2024Evaluating Moral Beliefs across LLMs through a Pluralistic Frameworkcited by 11
  12. 2024Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignmentcited by 10
  13. 2025MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Modelscited by 10
  14. 2025Exploring Persona-dependent LLM Alignment for the Moral Machine Experimentcited by 9
  15. 2025Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Moralitycited by 9
  16. 2026The Fragility Of Moral Judgment In Large Language Modelscited by 8
  17. 2025Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classificationcited by 7
  18. 2025MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanationcited by 7
  19. 2024Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detectioncited by 6
  20. 2024Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairnesscited by 6
  21. 2025Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalizationcited by 6
  22. 2025Telephone Surveys Meet Conversational AI: Evaluating a LLM-Based Telephone Survey System at Scalecited by 5
  23. 2025AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Differencecited by 4
  24. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 4
  25. 2025Moral Susceptibility and Robustness under Persona Role-Play in Large Language Modelscited by 4
  26. 2026Tracing Moral Foundations in Large Language Modelscited by 4
  27. 2024Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignmentcited by 3
  28. 2024A Survey on Moral Foundation Theory and Pre-Trained Language Models: Current Advances and Challengescited by 3
  29. 2025Exploring Cultural Variations in Moral Judgments with Large Language Modelscited by 3
  30. 2025Differences in the Moral Foundations of Large Language Modelscited by 3
  31. 2026Are Language Models Sensitive to Morally Irrelevant Distractors?cited by 3
  32. 2025A Survey on Training-free Alignment of Large Language Modelscited by 2
  33. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistantscited by 2
  34. 2025Quantifying Data Contamination in Psychometric Evaluations of LLMscited by 2
  35. 2025Interaction Protocol Shapes Moral Judgment in Multi-Agent Debatecited by 2
  36. 2025Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretabilitycited by 2
  37. 2025The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Modelscited by 2
  38. 2026MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Modelscited by 2

50 most cited of 84 All 84 (JSON)