Modeling Arbitrarily Applicable Relational Responding with the Non-Axiomatic Reasoning System: A Machine Psychology Approach

2025-03-01

AI Summary

This paper addresses the challenges of context sensitivity and flexibility in relational symbolic learning for artificial general intelligence (AGI). Methodologically, it introduces the Arbitrary Applicable Relational Responding (AARR) computational model, grounded in the Non-Axiomatic Reasoning System (NARS). It is the first work to formally encode AARR’s three core behavioral properties—mutual entailment, combinatorial entailment, and transformation of stimulus functions—as emergent uncertain inference mechanisms within NARS, integrated with Relational Frame Theory (RFT) to enable dynamic, context-sensitive symbolic relation generation. Empirical evaluation demonstrates that the model successfully reproduces key human cognitive phenomena, including stimulus equivalence, functional transfer, and oppositional relational networks. It validates both logical derivation of untrained relations and context-driven semantic transformation. By bridging symbolic reasoning with behavioral cognition through a computationally tractable framework, the model establishes a novel, executable bridge between machine inference and behavioral psychology.

Technology Category

Reasoning under Uncertainty: Relational Probabilistic ModelsCognitive Modeling & Cognitive Systems: Symbolic RepresentationsMachine Learning: Statistical Relational/Logic Learning

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSearch and Retrieval-Augmented AI: Agentic searchEconomics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Arbitrarily Applicable Relational Responding (AARR) is a cornerstone of human language and reasoning, referring to the learned ability to relate symbols in flexible, context-dependent ways. In this paper, we present a novel theoretical approach for modeling AARR within an artificial intelligence framework using the Non-Axiomatic Reasoning System (NARS). NARS is an adaptive reasoning system designed for learning under uncertainty. By integrating principles from Relational Frame Theory - the behavioral psychology account of AARR - with the reasoning mechanisms of NARS, we conceptually demonstrate how key properties of AARR (mutual entailment, combinatorial entailment, and transformation of stimulus functions) can emerge from the inference rules and memory structures of NARS. Two theoretical experiments illustrate this approach: one modeling stimulus equivalence and transfer of function, and another modeling complex relational networks involving opposition frames. In both cases, the system logically demonstrates the derivation of untrained relations and context-sensitive transformations of stimulus significance, mirroring established human cognitive phenomena. These results suggest that AARR - long considered uniquely human - can be conceptually captured by suitably designed AI systems, highlighting the value of integrating behavioral science insights into artificial general intelligence (AGI) research.

Problem

• Modeling human-like relational reasoning in AI systems.
• Integrating Relational Frame Theory with Non-Axiomatic Reasoning System.
• Demonstrating AI's ability to mimic human cognitive phenomena.

Innovation

• Integrates Relational Frame Theory with NARS
• Models AARR using Non-Axiomatic Reasoning System
• Demonstrates context-sensitive stimulus transformations