mlsanityData to 14 Oct 2026

Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Era

arXiv 2507.13175 ↗First posted 17 Jul 2025cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

The advancement of powerful yet opaque large language models (LLMs) necessitates a fundamental revision of the philosophical criteria used to evaluate artificial moral agents (AMAs). Pre-LLM frameworks often relied on the assumption of transparent architectures, which LLMs defy due to their stochastic outputs and opaque internal states. This paper argues that traditional ethical criteria are pragmatically obsolete for LLMs due to this mismatch. Engaging with core themes in the philosophy of technology, this paper proffers a revised set of ten functional criteria to evaluate LLM-based artificial moral agents: moral concordance, context sensitivity, normative integrity, metaethical awareness, system resilience, trustworthiness, corrigibility, partial transparency, functional autonomy, and moral imagination. These guideposts, applied to what we term "SMA-LLS" (Simulating Moral Agency through Large Language Systems), aim to steer AMAs toward greater alignment and beneficial societal integration in the coming years. We illustrate these criteria using hypothetical scenarios involving an autonomous public bus (APB) to demonstrate their practical applicability in morally salient contexts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 16 of its 59 references that are in the map. First posted on arXiv 17 Jul 2025.

Builds on

16 of 59 references.

References · 16

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  3. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  4. 2020Artificial Intelligence, Values and Alignmentcited by 448
  5. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 364
  6. 2023Cultural Bias and Cultural Alignment of Large Language Modelscited by 149
  7. 2024Collective Constitutional AI: Aligning a Language Model with Public Inputcited by 123
  8. 2023Generative Language Models Exhibit Social Identity Biasescited by 111
  9. 2023Deception Abilities Emerged in Large Language Modelscited by 101
  10. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them incited by 46
  11. 2024Moral Alignment for LLM Agentscited by 39
  12. 2023Language Model Alignment with Elastic Resetcited by 34
4 more
  1. 2024Assessing Political Bias in Large Language Modelscited by 32
  2. 2024Attributions toward Artificial Agents in a modified Moral Turing Testcited by 18
  3. 2023Minimum Levels of Interpretability for Artificial Moral Agentscited by 5
  4. 2024PADTHAI-MM: Principles-based Approach for Designing Trustworthy, Human-centered AI using MAST Methodologycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants
  2. 2023Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto
  3. 2024MoralBench: Moral Evaluation of LLMs
  4. 2025Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
  5. 2024Informed AI Regulation: Comparing the Ethical Frameworks of Leading LLM Chatbots Using an Ethics-Based Audit to Assess Moral Reasoning and Normative Values
  6. 2025The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach
  7. 2025Auditing the Ethical Logic of Generative AI Models
  8. 2026Incoherent by Design? On the Moral Self-Consistency of LLMs