mlsanityData to 7 Oct 2026

Minimum Levels of Interpretability for Artificial Moral Agents

arXiv 2307.00660 ↗First posted 2 Jul 2023cs.AI cs.CYcited by 5

Not on the map. Why?

Abstract (arXiv)

As artificial intelligence (AI) models continue to scale up, they are becoming more capable and integrated into various forms of decision-making systems. For models involved in moral decision-making, also known as artificial moral agents (AMA), interpretability provides a way to trust and understand the agent's internal reasoning mechanisms for effective use and error correction. In this paper, we provide an overview of this rapidly-evolving sub-field of AI interpretability, introduce the concept of the Minimum Level of Interpretability (MLI) and recommend an MLI for various types of agents, to aid their safe deployment in real-world settings.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 49 of its 141 references that are in the map. First posted on arXiv 2 Jul 2023.

Builds on

49 of 141 references.

References · 49

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  4. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  6. 2021Ethical and social risks of harm from Language Modelscited by 957
  7. 2023Progress measures for grokking via mechanistic interpretabilitycited by 822
  8. 2022A Generalist Agentcited by 802
  9. 2016The Mythos of Model Interpretabilitycited by 716
  10. 2020Aligning AI With Shared Human Valuescited by 706
  11. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  12. 2022Large Language Models Can Self-Improvecited by 656
37 more
  1. 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 585
  2. 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 564
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  5. 2023Augmented Language Models: a Surveycited by 398
  6. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  7. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  8. 2020Experience Grounds Languagecited by 241
  9. 2022Predictability and Surprise in Large Generative Modelscited by 209
  10. 2020Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernelcited by 185
  11. 2023GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Modelscited by 174
  12. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  13. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  14. 2022Explanations Can Reduce Overreliance on AI Systems During Decision-Makingcited by 111
  15. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  16. 2022Language Model Cascadescited by 104
  17. 2020Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligencecited by 100
  18. 2022When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentcited by 93
  19. 2021Characterizing Fairness Over the Set of Good Models Under Selective Labelscited by 65
  20. 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
  21. 2022A Generalist Neural Algorithmic Learnercited by 58
  22. 2021Grounding 'Grounding' in NLPcited by 44
  23. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
  24. 2021Medical Dead-ends and Learning to Identify High-risk States and Treatmentscited by 28
  25. 2018Building Ethically Bounded AIcited by 22
  26. 2021Ethics as a service: a pragmatic operationalisation of AI Ethicscited by 19
  27. 2022Towards Understanding Fairness and its Composition in Ensemble Machine Learningcited by 17
  28. 2021A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanationscited by 16
  29. 2020Causal Multi-Level Fairnesscited by 13
  30. 2023Active Reward Learning from Multiple Teacherscited by 13
  31. 2021Allocating Opportunities in a Dynamic Model of Intergenerational Mobilitycited by 12
  32. 2023ProKnow: Process Knowledge for Safety Constrained and Explainable Question Generation for Mental Health Diagnostic Assistancecited by 10
  33. 2021Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agentscited by 6
  34. 2021Have a break from making decisions, have a MARS: The Multi-valued Action Reasoning Systemcited by 6
  35. 2023Fairness and Sequential Decision Making: Limits, Lessons, and Opportunitiescited by 5
  36. 2015Adaptive Ensemble Learning with Confidence Boundscited by 4
  37. 2022Breaking Bad News in the Era of Artificial Intelligence and Algorithmic Medicine: An Exploration of Disclosure and its Ethical Justification using the Hedonic Calculuscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 2.

5 papers.

  1. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  2. 2025Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisionscited by 9
  3. 2024Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agentscited by 8
  4. 2024Can a Machine be Conscious? Towards Universal Criteria for Machine Consciousnesscited by 1
  5. 2025Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Eracited by 0