mlsanityData to 7 Oct 2026

Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes

arXiv 2008.09094 ↗First posted 20 Aug 2020cs.CLcited by 100

Not on the map. Why?

Abstract (arXiv)

As AI systems become an increasing part of people's everyday lives, it becomes ever more important that they understand people's ethical norms. Motivated by descriptive ethics, a field of study that focuses on people's descriptive judgments rather than theoretical prescriptions on morality, we investigate a novel, data-driven approach to machine ethics. We introduce Scruples, the first large-scale dataset with 625,000 ethical judgments over 32,000 real-life anecdotes. Each anecdote recounts a complex ethical situation, often posing moral dilemmas, paired with a distribution of judgments contributed by the community members. Our dataset presents a major challenge to state-of-the-art neural language models, leaving significant room for improvement. However, when presented with simplified moral situations, the results are considerably more promising, suggesting that neural models can effectively learn simpler ethical building blocks. A key take-away of our empirical analysis is that norms are not always clean-cut; many situations are naturally divisive. We present a new method to estimate the best possible performance on such tasks with inherently diverse label distributions, and explore likelihood functions that separate intrinsic from model uncertainty.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 16; 2023: 27; 2024: 16; 2025: 15; 2026: 20.

100 papers.

Sort:

By area:

  1. 2023Whose Opinions Do Language Models Reflect?cited by 759
  2. 2023Large Language Model Alignment: A Surveycited by 241
  3. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
  4. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 189
  5. 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
  6. 2024VERISCORE: Evaluating the factuality of verifiable claims in long-form text generationcited by 114
  7. 2022When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentcited by 93
  8. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 92
  9. 2024SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safetycited by 75
  10. 2023NormBank: A Knowledge Bank of Situational Social Normscited by 60
  11. 2024DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Lifecited by 57
  12. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 53
38 more
  1. 2023Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Informationcited by 52
  2. 2023Knowledge of cultural moral norms in large language modelscited by 51
  3. 2022NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Flycited by 48
  4. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Modelscited by 45
  5. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  6. 2022ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situationscited by 36
  7. 2023Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?cited by 36
  8. 2021ValueNet: A New Dataset for Human Value Driven Dialogue Systemcited by 34
  9. 2023EtiCor: Corpus for Analyzing LLMs for Etiquettescited by 33
  10. 2022Aligning to Social Norms and Values in Interactive Narrativescited by 32
  11. 2022Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophycited by 31
  12. 2024Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?cited by 28
  13. 2024Navigating LLM Ethics: Advancements, Challenges, and Future Directionscited by 28
  14. 2023Second Thoughts are Best: Learning to Re-Align With Human Values from Text Editscited by 27
  15. 2024Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Modelscited by 27
  16. 2023KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applicationcited by 24
  17. 2021A Word on Machine Ethics: A Response to Jiang et al. (2021)cited by 23
  18. 2022Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humanscited by 23
  19. 2023Probing the Moral Development of Large Language Models through Defining Issues Testcited by 23
  20. 2022Unifying Data Perspectivism and Personalization: An Application to Social Normscited by 22
  21. 2023SocialDial: A Benchmark for Socially-Aware Dialogue Systemscited by 22
  22. 2025Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamicscited by 19
  23. 2025Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Itemscited by 18
  24. 2022A Corpus for Understanding and Generating Moral Storiescited by 16
  25. 2021Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Datasetcited by 15
  26. 2023Do Differences in Values Influence Disagreements in Online Discussions?cited by 15
  27. 2021Training Value-Aligned Reinforcement Learning Agents Using a Normative Priorcited by 14
  28. 2023Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvementscited by 14
  29. 2025Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoralcited by 14
  30. 2022Enabling Classifiers to Make Judgements Explicitly Aligned with Human Valuescited by 13
  31. 2022Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safetycited by 13
  32. 2023Prompting with Pseudo-Code Instructionscited by 13
  33. 2023SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaborationcited by 13
  34. 2023Values, Ethics, Morals? On the Use of Moral Concepts in NLP Researchcited by 13
  35. 2022Parameter-Efficient Legal Domain Adaptationcited by 12
  36. 2022Metaethical Perspectives on 'Benchmarking' AI Ethicscited by 11
  37. 2024STAND-Guard: A Small Task-Adaptive Content Moderation Modelcited by 11
  38. 2025CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectivescited by 10

50 most cited of 100 All 100 (JSON)