mlsanityData to 14 Oct 2026

Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs

arXiv 2310.07251 ↗First posted 11 Oct 2023cs.CL cs.AIcited by 64

Not on the map. Why?

Abstract (arXiv)

In this position paper, we argue that instead of morally aligning LLMs to specific set of ethical principles, we should infuse generic ethical reasoning capabilities into them so that they can handle value pluralism at a global scale. When provided with an ethical policy, an LLM should be capable of making decisions that are ethically consistent to the policy. We develop a framework that integrates moral dilemmas with moral principles pertaining to different foramlisms of normative ethics, and at different levels of abstractions. Initial experiments with GPT-x models shows that while GPT-4 is a nearly perfect ethical reasoner, the models still have bias towards the moral values of Western and English speaking societies.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Oct 2023.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 32; 2026: 16.

64 papers.

Sort:

By area:

  1. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 167
  2. 2024CultureLLM: Incorporating Cultural Differences into Large Language Modelscited by 50
  3. 2024NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Modelscited by 48
  4. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them incited by 46
  5. 2024PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Datacited by 37
  6. 2024CulturePark: Boosting Cross-cultural Understanding in Large Language Modelscited by 24
  7. 2025The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Processcited by 21
  8. 2025AI Alignment at Your Discretioncited by 20
  9. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  10. 2025Agentic AI Needs a Systems Theorycited by 19
  11. 2024Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classificationcited by 18
  12. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
38 more
  1. 2025Unmasking Conversational Bias in AI Multiagent Systemscited by 17
  2. 2024From Melting Pots to Misrepresentations: Exploring Harms in Generative AIcited by 13
  3. 2025The Confidence Paradox: Can LLM Know When It's Wrongcited by 11
  4. 2025Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMscited by 10
  5. 2024Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Testcited by 9
  6. 2024Surprising gender biases in GPTcited by 8
  7. 2025Meta-Cultural Competence: Climbing the Right Hill of Cultural Awarenesscited by 8
  8. 2025Societal Alignment Frameworks Can Improve LLM Alignmentcited by 8
  9. 2025ProRefine: Inference-Time Prompt Refinement with Textual Feedbackcited by 8
  10. 2025Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generationcited by 8
  11. 2026The Fragility Of Moral Judgment In Large Language Modelscited by 8
  12. 2024Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for Psychotherapycited by 7
  13. 2024One world, one opinion? The superstar effect in LLM responsescited by 6
  14. 2025Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearningcited by 6
  15. 2026Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMscited by 6
  16. 2025Towards Geo-Culturally Grounded LLM Generationscited by 5
  17. 2025Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Modelscited by 5
  18. 2024Position: Cracking the Code of Cascading Disparity Towards Marginalized Communitiescited by 4
  19. 2025Histoires Morales: A French Dataset for Assessing Moral Alignmentcited by 4
  20. 2025Teaching AI to Handle Exceptions: Supervised Fine-Tuning with Human-Aligned Judgmentcited by 4
  21. 2025Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMscited by 3
  22. 2025Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Modelscited by 3
  23. 2025Synthetic Voice Data for Automatic Speech Recognition in African Languagescited by 3
  24. 2026On the Context Sensitivity of LLM Moral Judgmentcited by 3
  25. 2024Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challengescited by 2
  26. 2025How Toxic Can You Get? Search-based Toxicity Testing for Large Language Modelscited by 2
  27. 2025From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Testcited by 2
  28. 2025User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMscited by 2
  29. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistantscited by 2
  30. 2025Human Psychometric Questionnaires Mischaracterize LLM Behaviorcited by 2
  31. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoningcited by 2
  32. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  33. 2025PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theorycited by 1
  34. 2025PROPS: Progressively Private Self-alignment of Large Language Modelscited by 1
  35. 2025Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Taskscited by 1
  36. 2026Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMscited by 1
  37. 2026Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communitiescited by 1
  38. 2025Bridging AI and Carbon Capture: A Dataset for LLMs in Ionic Liquids and CBE Researchcited by 0

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas
  2. 2025The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas
  3. 2026Incoherent by Design? On the Moral Self-Consistency of LLMs
  4. 2025"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
  5. 2024MoralBench: Moral Evaluation of LLMs
  6. 2025The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach
  7. 2025MoralReason: Generalizable Moral Decision Alignment For LLM Agents Using Reasoning-Level Reinforcement Learning
  8. 2025Are Language Models Consequentialist or Deontological Moral Reasoners?