mlsanityData to 7 Oct 2026

A Word on Machine Ethics: A Response to Jiang et al. (2021)

arXiv 2111.04158 ↗First posted 7 Nov 2021cs.CL cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Ethics is one of the longest standing intellectual endeavors of humanity. In recent years, the fields of AI and NLP have attempted to wrangle with how learning systems that interact with humans should be constrained to behave ethically. One proposal in this vein is the construction of morality models that can take in arbitrary text and output a moral judgment about the situation described. In this work, we focus on a single case study of the recently proposed Delphi model and offer a critique of the project's proposed method of automating morality judgments. Through an audit of Delphi, we examine broader issues that would be applicable to any similar attempt. We conclude with a discussion of how machine ethics could usefully proceed, by focusing on current and near-future uses of technology, in a way that centers around transparency, democratic values, and allows for straightforward accountability.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 15 of its 43 references that are in the map. First posted on arXiv 7 Nov 2021.

Builds on

15 of 43 references.

References · 15

  1. 2018Datasheets for Datasetscited by 1,371
  2. 2020Aligning AI With Shared Human Valuescited by 706
  3. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  4. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  5. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  6. 2019Queens are Powerful too: Mitigating Gender Bias in Dialogue Generationcited by 152
  7. 2020Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequencescited by 133
  8. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 102
  9. 2020Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotescited by 100
  10. 2020Multi-Dimensional Gender Bias Classificationcited by 80
  11. 2021Anticipating Safety Issues in E2E Conversational AI: Framework and Toolingcited by 77
  12. 2016The AGI Containment Problemcited by 36
3 more
  1. 2020Exploring the Linear Subspace Hypothesis in Gender Bias Mitigationcited by 25
  2. 2021Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue modelscited by 23
  3. 2020Robot Rights? Let's Talk about Human Welfare Insteadcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 13; 2023: 5; 2024: 4; 2025: 1.

23 papers.

Sort:

By area:

  1. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  2. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  3. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  4. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
  5. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 92
  6. 2022Perturbation Augmentation for Fairer NLPcited by 51
  7. 2023Knowledge of cultural moral norms in large language modelscited by 51
  8. 2022NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Flycited by 48
  9. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Taskscited by 44
  10. 2022Speaking Multiple Languages Affects the Moral Bias of Language Modelscited by 34
  11. 2022Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophycited by 31
  12. 2022Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humanscited by 23
11 more
  1. 2023Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoningcited by 20
  2. 2022MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussionscited by 17
  3. 2022Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safetycited by 13
  4. 2023Values, Ethics, Morals? On the Use of Moral Concepts in NLP Researchcited by 13
  5. 2022Natural Language Deduction with Incomplete Informationcited by 12
  6. 2024Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experimentcited by 11
  7. 2022Towards Answering Open-ended Ethical Quandary Questionscited by 3
  8. 2024SaGE: Evaluating Moral Consistency in Large Language Modelscited by 3
  9. 2024Intuitions of Compromise: Utilitarianism vs. Contractualismcited by 1
  10. 2023Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the UScited by 0
  11. 2025Practising responsibility: Ethics in NLP as a hands-on coursecited by 0