Moral Reasoning

Follow this topic Ask about this topic

Moral reasoning studies how people and AI systems judge actions, explain obligations, and resolve conflicts among values such as harm, fairness, loyalty, and autonomy. Researchers use philosophical formalisms—including deontic logic, contractualist argumentation, and norm-guided planning—alongside psychological frameworks such as Moral Foundations Theory, human surveys, and dilemma benchmarks. For language models, evaluations vary prompts, context, language, and interaction, while interpretability methods probe or steer internal representations and measure uncertainty rather than forcing annotator disagreement into a single label. A central open problem is that judgments shift with framing and culture, and no agreed target captures plural moral values while remaining consistent, robust, and useful in real decisions.

Latest papers

45 papers2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Justice After Identity: Large Language Models and the View from Everywhere
Oct 6, 2026W. Russell NeumanMoral Reasoning in Language Models Moral Reasoning
Formalizing the Moral Evaluation of Speech Acts: Truthfulness, Lies and Ethical Dilemmas
Oct 3, 2026Benjamin Icard, Gauvain Bourgne, Jeanne Bonnaventure +1Moral Reasoning
LIP6, Sorbonne University, CNRS, France
Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment
Sep 18, 2026Maciej SkorskiAnnotator Disagreement Algorithmic Auditing
University of Luxembourg
Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30
Sep 18, 2026Hans Andersen, David DichasLanguage Model Steering Moral Reasoning in Language Models
Moral Rebel Agents: Decision-Making Under Conflicting Obligations
Sep 13, 2026Hector Munoz-Avila, David W. Aha, Paola RizzoAI Ethics Moral Reasoning
Computer Science & Engineering; Lehigh University; Bethlehem, PA USA · Navy Center for Applied Research in AI; Naval Research Laboratory; Washington, DC USA · Interagens s.r.l.; Rome Italy
Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour
Sep 3, 2026Huixiang Fu, Marian-Andrei RizoiuSocial Media Analysis Moral Reasoning
Behavioral Data Science, University of Technology Sydney
How Language Models Organize and Structure Moral Knowledge
Aug 27, 2026Orion Reblitz-RichardsonMoral Reasoning Representation Geometry in Language Models
Distiller Labs
Metanormative Theory for RL-Based Moral Agents
Aug 8, 2026Aleks Knoks, Marija SlavkovikAI Alignment AI Ethics
University of Luxembourg, 2, place de l’Université, L-4365, Esch-sur-Alzette, Luxembourg · University of Bergen, Fosswinckelsgt. 6, 5007 Bergen, Norway
CORDA: A Benchmark for Hierarchical Harm-Centric Moral Reasoning in Large Language Models
Aug 8, 2026Siddarth Singh, Victoria Williams, Simon Rosen +6LLM Evaluation Moral Reasoning in Language Models
University of the Witwatersrand, Johannesburg, South Africa
A Contractualist Argumentation Framework for Moral Decision-Making
Aug 3, 2026Luis Marcos-Vidal, Giulio Antonio Abbo, Tony BelpaemeComputational Argumentation Moral Reasoning
Hospital del Mar Research Institute, Barcelona, Spain · IDLab-AIRO, Ghent University – imec, Ghent, Belgium
D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios
Jul 22, 2026Siyi Hao, Yidi Cao, Linhao Yu +2LLM Evaluation LLM Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · The International Joint Institute of Tianjin University, Fuzhou, China
Moral Attitudes of Sentient ASI towards Humanity and Implications for AGI Development
Jul 16, 2026Jean-Paul Van BelleAI Alignment AI Ethics
University of Cape Town, Rondebosch, South Africa
Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?
Jun 30, 2026Jongchan Choi, Nari Yang, Sung Soo Park +4LLM Evaluation Moral Reasoning in Language Models
1Korea University · 2XenoStep AI · 3Hankuk University of Foreign Studies
A Virtuous AI is an Existential Risk
Jun 11, 2026Guillermo Del Pinal, Youngchan Lee, Min OhnLLM Safety Alignment AI Agent Safety
University of Massachusetts Amherst
Are LLMs Bad at Moral Reasoning?
Jun 10, 2026Menghang Zhu, Seth LazarAutomatic Rubric Generation LLM Evaluation
School of Philosophy (Political Philosophy) Renmin University of China · School of Government and Policy Johns Hopkins University
Accounting for Context: Shaping Moral Credences for Value Alignment
Jun 5, 2026Jazon Szabo, Sanjay ModgilPluralistic Alignment Decision-Making under Uncertainty
King’s College London, UK
Is LLM's Moral Decision Compositional?
May 29, 2026Weijia Zhang, Ruiqi Chen, Yunze Xiao +1LLM Evaluation Moral Reasoning in Language Models
University of Illinois Urbana-Champaign · University of Michigan · Carnegie Mellon University +1
Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI
May 27, 2026Aisha Aijaz, Rahul Goel, Arnav Batra +1Stacked Ensemble Learning Moral Reasoning
Department of Computer Science and Engineering, IIIT Delhi, New Delhi, Delhi, 110020, India · Mehta Family School of Data Science and AI, IIT Palakkad, Palakkad, Kerala, 678623, India
Reasoning and Planning with Dynamically Changing Norms
May 26, 2026Taylor Olson, Roberto Salas-Damian, Kenneth D. ForbusSymbolic Planning AI Agent Safety
University of Iowa · Northwestern University
An Algebraic Exposition of the Theory of Dyadic Morality
May 15, 2026Kush R. VarshneyComputational Cognitive Modeling Moral Reasoning
IBM Research, Yorktown Heights, NY, USA
StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
May 12, 2026Ishmam Khan, Sindhuja Thogarrati, Shuo ZhangLLM Alignment LLM Fine-Tuning
Tufts University · Bose Corporation
How Does Thinking Mode Change LLM Moral Judgments? A Controlled Instant-vs-Thinking Comparison Across Five Frontier Models
May 6, 2026Sai Sourabh MadurLLM Evaluation Moral Reasoning in Language Models
Independent researcher (ex-Meta)
An Ethical eValuation Agent (EeVA): Results of a Proof-of-Concept Test on a Prototype Agentic-like Workflow to Assist Ethical Deliberations
May 5, 2026Stephen Milford, B. Zara Malgir, Miguel VazquezAI-Assisted Decision Making LLM Agents
Institute for Biomedical Ethics, Basel University, Switzerland · Barcelona Supercomputing Center
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
May 5, 2026Chenchen Yuan, Zheyu Zhang, Gjergji KasneciLLM Alignment Moral Reasoning in Language Models
School of Computation, Information and Technology, Technical University of Munich · School of Social Sciences and Technology, Technical University of Munich · Munich Center for Machine Learning (MCML)
Are You the A-hole? A Fair, Multi-Perspective Ethical Reasoning Framework
Apr 30, 2026Sheza Munir, Ahanaf Rodoshi, Sumin Lee +3Annotator Disagreement Neuro-Symbolic Reasoning
Computer Science, University of Toronto
Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training
Apr 30, 2026Jasmine Brazilek, Juliana SeawellMoral Reasoning in Language Models RL Post-Training
†Compassion Aligned Machine Learning (CaML)
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
Apr 27, 2026Benjamin Minhao Chen, Xinyu XieHuman Preference Evaluation AI Alignment
The University of Hong Kong, Hong Kong, China
Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions
Apr 23, 2026Jiseon Kim, Jea Kwon, Luiz Felipe Vecchietti +3Moral Reasoning in Language Models Human Behavior Simulation
1KAIST · 2MPI-SP
Brief chatbot interactions produce lasting changes in human moral values
Apr 23, 2026Yue Teng, Qianer Zhong, Kim Mai Tich Nguyen Thordsen +2Conversational Agents Moral Reasoning
Department of Psychology, The University of Hong Kong, Hong Kong SAR, China. · Techno-Entrepreneurship Core, The University of Hong Kong, Hong Kong SAR, China. · Department of Psychology, University of Copenhagen, Copenhagen, Denmark. +4
Do Emotions Influence Moral Judgment in Large Language Models?
Apr 21, 2026Mohammad Saim, Tianyu JiangLLM Evaluation Moral Reasoning in Language Models
University of Cincinnati

Oct 6, 2026J/K move · Enter open · S save

Justice After Identity: Large Language Models and the View from Everywhere

W. Russell Neuman

Moral Reasoning in Language Models Moral Reasoning Human-AI Decision Making Algorithmic Fairness

Open paper AskPDF arXiv

The search for a common view of justice and fairness has challenged human collective activity, as our diverging judgments are unavoidably shaped by the self-interests of social position, personal benefit, cultural inheritance, and historical circumstance. John Rawls famously attempted to overcome this limitation through popularizing a philosophical tradition known by the phrase "the original position" - a thought experiment by which people select principles of justice without knowing the identities or advantages they will possess. Critics, however, have long questioned whether people can meaningfully suspend their social identities and suppress morally relevant forms of lived experience. Artificial intelligence engaged to calculate algorithmic and agentic fairness introduces a novel possibility. LLMs have no singular class, race, gender, nationality, or biography, yet their parameters encode linguistic representations of a vast range of human identities and moral traditions. Perhaps the ethical judgments of LLMs could approximate an integrative original position - a "view from everywhere" generated not by excluding social identities but by computationally incorporating their diversity.It is unlikely that humankind will "hand over the keys" to computational systems by simply delegating complete agentic control of distributive and procedural collective processes. But AI may play a role, perhaps a positive one, interacting with individual and collective human judgment as we often confront increasingly polarized views on what is fair and just. We present data comparing human, base model, and frontier/fine-tuned model judgments about classic moral dilemmas while systematically varying identity relationships and Rawlsian constraints on identity. We conclude by speculating whether, if advanced AI systems provide humans with thoughtful advice, humans would actually be likely to accept it.