Arbitrarily Applicable Same/Opposite Relational Responding with NARS

2025-05-11

AI Summary

This paper addresses the challenge of achieving human-level flexible relational generalization in Non-Axiomatic Reasoning Systems (NARS). We propose the “acquired relations” mechanism—the first approach to introduce dynamically constructible, reciprocal, and compositionally composable relational representations within NARS. Our method integrates the matching-to-sample (MTS) paradigm with internal confidence modeling, enabling rapid internalization of symmetry (e.g., “same”) and opposition (e.g., “opposite”) relations from minimal explicit training. Crucially, it supports cross-relational inference—e.g., spontaneously deriving “same” from multiple “opposite” instances. Experiments demonstrate high accuracy on relational generalization tasks, and the system’s confidence evolution closely matches human cognitive data. This significantly enhances NARS’s context-sensitive, domain-agnostic relational reasoning capability in symbolic cognition, advancing its capacity for adaptive, open-ended conceptual learning.

Technology Category

Cognitive Modeling & Cognitive Systems: Conceptual Inference and ReasoningKnowledge Representation and Reasoning: Knowledge AcquisitionReasoning under Uncertainty: Relational Probabilistic Models

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Same/opposite relational responding, a fundamental aspect of human symbolic cognition, allows the flexible generalization of stimulus relationships based on minimal experience. In this study, we demonstrate the emergence of extit{arbitrarily applicable} same/opposite relational responding within the Non-Axiomatic Reasoning System (NARS), a computational cognitive architecture designed for adaptive reasoning under uncertainty. Specifically, we extend NARS with an implementation of extit{acquired relations}, enabling the system to explicitly derive both symmetric (mutual entailment) and novel relational combinations (combinatorial entailment) from minimal explicit training in a contextually controlled matching-to-sample (MTS) procedure. Experimental results show that NARS rapidly internalizes explicitly trained relational rules and robustly demonstrates derived relational generalizations based on arbitrary contextual cues. Importantly, derived relational responding in critical test phases inherently combines both mutual and combinatorial entailments, such as deriving same-relations from multiple explicitly trained opposite-relations. Internal confidence metrics illustrate strong internalization of these relational principles, closely paralleling phenomena observed in human relational learning experiments. Our findings underscore the potential for integrating nuanced relational learning mechanisms inspired by learning psychology into artificial general intelligence frameworks, explicitly highlighting the arbitrary and context-sensitive relational capabilities modeled within NARS.

Problem

• Demonstrating arbitrarily applicable same/opposite relational responding in NARS
• Extending NARS with acquired relations for symmetric and novel relational combinations
• Integrating human-inspired relational learning into artificial general intelligence

Innovation

• Extends NARS with acquired relations implementation
• Enables symmetric and novel relational combinations
• Demonstrates derived relational generalizations robustly