mlsanityData to 14 Oct 2026

Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values

arXiv 2506.00079 ↗First posted 30 May 2025cs.CY cs.AI cs.LGcited by 2

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

The rapid integration of Large Language Models (LLMs) in high-stakes decision-making -- such as allocating scarce resources like donor organs -- raises critical questions about their alignment with human moral values. We systematically evaluate the behavior of several prominent LLMs against human preferences in kidney allocation scenarios and show that LLMs: i) exhibit stark deviations from human values in prioritizing various attributes, and ii) in contrast to humans, LLMs rarely express indecision, opting for deterministic decisions even when alternative indecision mechanisms (e.g., coin flipping) are provided. Nonetheless, we show that low-rank supervised fine-tuning with few samples is often effective in improving both decision consistency and calibrating indecision modeling. These findings illustrate the necessity of explicit alignment strategies for LLMs in moral/ethical domains.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 36 of its 80 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

36 of 80 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making9 Oct
  2. 2024Moral Alignment for LLM Agents2 Oct
  3. 2024ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs15 Sep
  4. 2022Fine-tuning language models to find agreement among humans with diverse preferences28 Nov

Other references · 32

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  3. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  4. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  5. 2024Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Modelscited by 162
  6. 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoningcited by 154
  7. 2021Can Machines Learn Morality? The Delphi Experimentcited by 141
  8. 2022When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentcited by 93
  9. 2024Are Large Language Models Consistent over Value-laden Questions?cited by 58
  10. 2024Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Modelscited by 57
  11. 2025Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactionscited by 52
  12. 2025Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?cited by 51
20 more
  1. 2024MoralBench: Moral Evaluation of LLMscited by 50
  2. 2024Forcing Diffuse Distributions out of Language Modelscited by 48
  3. 2024A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicinecited by 45
  4. 2023Exploring the psychology of LLMs' Moral and Legal Reasoningcited by 44
  5. 2023Generative Social Choicecited by 43
  6. 2024Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Contextcited by 41
  7. 2020Adapting a Kidney Exchange Algorithm to Align with Human Valuescited by 36
  8. 2025Normative Evaluation of Large Language Models with Everyday Moral Dilemmascited by 24
  9. 2025Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancycited by 17
  10. 2025Personality-Driven Decision-Making in LLM-Based Autonomous Agentscited by 13
  11. 2025Generative Social Choice: The Next Generationcited by 10
  12. 2025Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisionscited by 9
  13. 2020Indecision Modelingcited by 8
  14. 2024On The Stability of Moral Preferences: A Problem with Computational Elicitation Methodscited by 7
  15. 2024Right vs. Right: Can LLMs Make Tough Choices?cited by 6
  16. 2025Susceptibility of Large Language Models to User-Driven Factors in Medical Queriescited by 6
  17. 2025Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulationscited by 5
  18. 2025None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answeringcited by 5
  19. 2025The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approachcited by 3
  20. 2025Psychological Counseling Ability of Large Language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedbackcited by 6
  2. 2026Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Valuescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
  2. 2025The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  3. 2025Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
  4. 2024Language Model Alignment in Multilingual Trolley Problems
  5. 2026CORDA: A Benchmark for Hierarchical Harm-Centric Moral Reasoning in Large Language Models
  6. 2026Scaling Laws for Moral Machine Judgment in Large Language Models
  7. 2025Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
  8. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants