mlsanityData to 14 Oct 2026

The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making

arXiv 2410.07304 ↗First posted 9 Oct 2024cs.HC cs.AIcited by 12

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

Abstract (arXiv)

As large language models (LLMs) become increasingly integrated into society, their alignment with human morals is crucial. To better understand this alignment, we created a large corpus of human- and LLM-generated responses to various moral scenarios. We found a misalignment between human and LLM moral assessments; although both LLMs and humans tended to reject morally complex utilitarian dilemmas, LLMs were more sensitive to personal framing. We then conducted a quantitative user study involving 230 participants (N=230), who evaluated these responses by determining whether they were AI-generated and assessed their agreement with the responses. Human evaluators preferred LLMs' assessments in moral scenarios, though a systematic anti-AI bias was observed: participants were less likely to agree with judgments they believed to be machine-generated. Statistical and NLP-based analyses revealed subtle linguistic differences in responses, influencing detection and agreement. Overall, our findings highlight the complexities of human-AI perception in morally charged decision-making.

Key facts. Cited by 12 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 17 of its 56 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

17 of 56 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Strong and weak alignment of large language models with human values5 Aug
  2. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference7 Mar
  3. 2020Aligning AI With Shared Human Values5 Aug

Other references · 14

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  3. 2022Using cognitive psychology to understand GPT-3cited by 398
  4. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  5. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  6. 2022Human heuristics for AI-generated language are flawedcited by 105
  7. 2024(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advicecited by 63
  8. 2023Does GPT-4 pass the Turing test?cited by 37
  9. 2024Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challengescited by 30
  10. 2024AI-AI Bias: large language models favor communications generated by large language modelscited by 26
  11. 2024Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choicecited by 12
  12. 2024A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Healthcited by 7
2 more
  1. 2024Sleeper Social Bots: a new generation of AI disinformation bots are already a political threatcited by 3
  2. 2020"Do the Right Thing" for Whom? An Experiment on Ingroup Favouritism, Group Assorting and Moral Suasioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 3.

12 papers.

  1. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 36
  2. 2026Large Language Model Reasoning Failurescited by 21
  3. 2025Large Language Models Do Not Simulate Human Psychologycited by 19
  4. 2025Strategic Tradeoffs Between Humans and AI in Multi-Agent Bargainingcited by 11
  5. 2025To Mask or to Mirror: Human-AI Alignment in Collective Reasoningcited by 5
  6. 2025Localizing Persona Representations in LLMscited by 3
  7. 2025Interaction Protocol Shapes Moral Judgment in Multi-Agent Debatecited by 3
  8. 2025Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Valuescited by 2
  9. 2025Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Modelscited by 1
  10. 2026Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Modelscited by 1
  11. 2025BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicatorscited by 0
  12. 2026Reliability Auditing for Downstream LLM tasks in Psychiatry: LLM-Generated Hospitalization Risk Scorescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Exploring the psychology of LLMs' Moral and Legal Reasoning
  2. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants
  3. 2025Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
  4. 2024MoralBench: Moral Evaluation of LLMs
  5. 2024Language Model Alignment in Multilingual Trolley Problems
  6. 2025The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis
  7. 2024Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses
  8. 2026Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments