Moral Reasoning in Language Models

Overview

The field examines how language models recognize moral stakes, choose between competing values, and apply judgments in settings such as trolley dilemmas, clinical resource allocation, and interpersonal advice. Researchers compare model decisions with human judgments and use multilingual, counterfactual, and multi-turn adversarial tests to probe cultural variation and robustness; methods range from prompting and fine-tuning to multi-agent debate and mechanistic analysis of internal representations. Models can produce persuasive ethical explanations, but their choices may shift with framing, language, social pressure, or conversation history, and explanations do not always predict behavior. A central challenge is improving consistency and resilience without imposing one narrow moral standard across culturally diverse people and situations.

Latest papers

CardsList

126 papers7 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

  1. AfriNORM: An Evaluation Benchmark for Normative Reasoning of LLMs Across African Cultures

    Nov 17, 2026Ahmad Samuel Gali, Tadesse Destaw Belay, Idris Abdulmumin +2Cross-Cultural Language Model EvaluationCultural Knowledge in Language Models

  2. Disambiguating Moral Circuits and Moral Features in Language Models: Moral content, normative judgment or cue words? Evidence from 14 models

    Nov 16, 2026Davide Liga, Liuwen Yu, Matteo MagniniMoral Reasoning in Language ModelsLLM Interpretability

  3. Do large language models rank moral values? A transitivity test of moral competence

    Nov 6, 2026Katelyn A. Wasson, Kiwon Song, James M. Jennings +3Moral Reasoning in Language ModelsLLM Evaluation

  4. ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective

    Nov 6, 2026Chaoran Li, Yukun Li, Zeyuan Zhao +3Moral Reasoning in Language ModelsAI Agent Safety Benchmarks

  5. Exploit or conform? How norm utility prompting changes the way LLMs use community beliefs

    Nov 2, 2026Leon Klingborg, Theodor Cimpeanu, Alexander J. StewartNormative Conformity in Language ModelsLLM Decision-Making

  6. Large language models underrepresent malice and overreport virtue

    Oct 31, 2026Xiaoyan Wu, Fan ShiMoral Reasoning in Language ModelsCognitive Bias in Language Models

  7. Deogen: Automatic Benchmark Generation for Reasoning over Policies

    Oct 28, 2026Sam Kouteili, William Liang, Keeran Murray +4Synthetic Benchmark GenerationLanguage Model Reasoning Evaluation

  8. MedConstBench: Benchmarking How Constitutions Steer LLMs in Medical Ethics

    Oct 27, 2026Yibo Yang, Zerui Huang, Haomiao Yang +1Medical LLMsMoral Reasoning in Language Models

  9. Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs

    Oct 14, 2026Adel Khorramrouz, Yi-Chia Wang, Sharon LevyAdversarial Attacks on LLMsLLM Safety Evaluation

  10. Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs

    Oct 12, 2026Eugenie ShiMoral Reasoning in Language ModelsLLM Interpretability

  11. Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices

    Sep 28, 2026Lucio La Cava, Andrea TagarelliMoral Reasoning in Language ModelsLLM Auditing

  12. Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models

    Sep 17, 2026Utkarsh Agarwal, Monojit ChoudhuryLLM AlignmentMoral Reasoning in Language Models

  13. FaithfulBench: Does AI Counsel Uphold or Undermine the User's Professed Faith?

    Sep 12, 2026M Waleed Kadous, Benjamin Olsen, Walter Scheirer +3Moral Reasoning in Language ModelsGenerative AI Evaluation

  14. Human-like moral judgments conceal divergent motive attributions in large language models

    Sep 7, 2026Xiaoyan Wu, Jean-Claude DreherLLM EvaluationMoral Reasoning in Language Models

  15. Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?

    Sep 4, 2026Daan R. Henselmans, Derck W. E. Prinzhorn, Arno LibertAI AccountabilityLanguage Model Auditing

  16. How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions

    Sep 4, 2026Fernanda Mansilla, Aloysius Tok, Bahia Guellaï +2Moral Reasoning in Language ModelsHuman-AI Decision Making

  17. Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment

    Sep 4, 2026Arno Libert, Derck W. E. Prinzhorn, Daan R. HenselmansLLM Safety AlignmentBehavioral Consistency of LLM Agents

  18. HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals

    Sep 3, 2026Jasmine Brazilek, Miles Tidmarsh, Matthias Endres +2Moral Reasoning in Language ModelsLLM Safety Alignment

  19. Representational alignment yields generalizable safety in language models

    Sep 3, 2026Lingyu Li, Yan Teng, Yingchun Wang +1Moral Reasoning in Language ModelsLLM Safety Alignment

  20. Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation

    Sep 3, 2026Yuhe Wu, Guangyu Wang, Yujie Chen +7Moral Reasoning in Language ModelsLLM Reliability

  21. Rare Diseases, Common Dilemmas: LLMs Prioritize Equal Resource Distribution over Patient Benefit in Decision-Making

    Aug 25, 2026Minda Zhao, Xu Han, Rishabh Goel +6Moral Reasoning in Language ModelsClinical Decision-Making