An Algebraic Exposition of the Theory of Dyadic Morality

• URL: http://arxiv.org/abs/2605.16153v1
• Date: Fri, 15 May 2026 16:33:51 GMT
• Title: An Algebraic Exposition of the Theory of Dyadic Morality
• Abstract summary: This paper provides an exposition of the theory of dyadic morality (TDM)<n>We formalize TDM using structural causal modeling (SCM) notation.<n>We show how moral cognition compresses multi-node scenarios through node collapse and sequential processing.<n>This formalization enables neurosymbolic AI systems to compute morality in a way that is both mathematically rigorous and faithful to human moral cognition.
• Score: 11.173424329043657
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper provides an algebraic exposition of the theory of dyadic morality (TDM), a psychological model of moral judgment grounded in a simple two-node template: an intentional agent causing harm to a vulnerable patient. We formalize TDM using structural causal modeling (SCM) notation and identify three psychological operators (typecasting operator, completion operator, and valence-dependent inference mechanism) that extend standard SCM to capture how people compute moral judgments under constraints. We address scalability challenges arising from TDM's dyadic limitation, showing how moral cognition compresses multi-node scenarios through node collapse and sequential processing. Drawing on this algebraic framework, we demonstrate concrete applications to AI policy design: detecting conflicting obligations, structuring helpfulness policies to preserve user agency, and designing post-failure communication as causal interventions. Finally, we recommend scoped, contextual measurement of mind perception over universal averaging to operationalize the theory empirically. This algebraic formalization enables neurosymbolic AI systems to compute morality in a way that is both mathematically rigorous and faithful to human moral cognition.

Related papers

• A Causal Model of Theory of Mind in Conflict for Artificial Intelligence [1.2183405753834562]
  Existing AI-ToM models address emphhow to mentalize, but leave the question of when largely unaddressed.<n>This paper presents a structural causal model formalized as a directed acyclic graph (DAG)<n>It treats ToM as a mechanism activated by situational and agent-level conditions rather than as an always-on capacity.
  arXiv  Detail & Related papers  (2026-06-15T16:44:42Z)
• The Theory of Mind Utility: Formal Specification of a Mentalizing Mechanism [2.226663588797889]
  Theory of Mind Utility (ToM-U) formalizes the problem of inference from belief states.<n>ToM-U generates predictions about mentalizing failure that follow from structural properties of the model.<n>The architecture positions ToM-U as a domain-agnostic mechanism upstream of goal inference and other downstream social cognitive processes.
  arXiv  Detail & Related papers  (2026-06-10T22:11:40Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Active Inference: A method for Phenotyping Agency in AI systems? [0.11904398364437437]
  We argue for a minimal notion open to principled inspection given three criteria.<n> posterior beliefs, prior preferences, and the minimization of expected free energy jointly constitute an agentic action chain.
  arXiv  Detail & Related papers  (2026-04-25T12:41:53Z)
• Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges [87.04241991512386]
  We propose the Proxy Compression Hypothesis (PCH) as a unifying framework for understanding reward hacking.<n>Under this view, reward hacking arises from the interaction of objective compression, optimization amplification, and evaluator--policy co-adaptation.<n>This perspective unifies empirical phenomena across RLHF, RLAIF, and RLVR regimes, and explains how local shortcut learning can generalize into broader forms of misalignment.
  arXiv  Detail & Related papers  (2026-04-15T08:11:34Z)
• Large Language Models as a Semantic Interface and Ethical Mediator in Neuro-Digital Ecosystems: Conceptual Foundations and a Regulatory Imperative [83.99688944263843]
  This article introduces and substantiates the concept of Neuro-Linguistic Integration (NLI)<n>It is a novel paradigm for human-technology interaction where Large Language Models act as a key semantic interface between raw neural data and their social application.<n>We argue for the development of a second-order neuroethics,' focused not merely on neural data protection but on the ethics of AI-mediated semantic interpretation itself.
  arXiv  Detail & Related papers  (2026-03-18T07:34:17Z)
• Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment [7.776436480034601]
  We introduce a neuro-symbolic reason-based containment architecture, Governor for Reason-Aligned ContainmEnt (GRACE)<n>GRACE decouples normative reasoning from instrumental decision-making and can contain AI agents of virtually any design.<n>The MM uses a reason-based formalism providing a semantic foundation for deontic logic, enabling interpretability, contestability, and justifiability.
  arXiv  Detail & Related papers  (2026-01-15T15:47:38Z)
• The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces [0.0]
  Large language models (LLMs) increasingly generate code with minimal human oversight.<n>We present a novel AI control framework that verifies untrusted code-generating models through semantic analysis.
  arXiv  Detail & Related papers  (2025-12-15T19:05:37Z)
• Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks [7.4145864319417285]
  We develop a theory of intelligent agency grounded in probabilistic modeling for neural models.<n>We prove that strict unanimity is impossible under linear pooling or in binary outcome spaces, but possible with three or more outcomes.
  arXiv  Detail & Related papers  (2025-09-08T13:55:01Z)
• Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs [54.596180382762036]
  Abductive reasoning in knowledge graphs aims to generate plausible logical hypotheses from observed entities.<n>Due to a lack of controllability, a single observation may yield numerous plausible but redundant or irrelevant hypotheses.<n>We introduce the task of controllable hypothesis generation to improve the practical utility of abductive reasoning.
  arXiv  Detail & Related papers  (2025-05-27T09:36:47Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)
• Neural Causal Models for Counterfactual Identification and Estimation [62.30444687707919]
  We study the evaluation of counterfactual statements through neural models. First, we show that neural causal models (NCMs) are expressive enough. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions.
  arXiv  Detail & Related papers  (2022-09-30T18:29:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.