Why Do We Need Neuro-symbolic AI to Model Pragmatic Analogies?

TL;DR

This paper argues that neuro-symbolic AI is essential for modeling complex pragmatic analogies, as it combines statistical and symbolic methods to enhance understanding and explanation beyond what large language models can achieve alone.

Contribution

It highlights the limitations of LLMs in handling complex analogies and advocates for neuro-symbolic AI techniques to improve analogy reasoning and interpretability.

Findings

LLMs struggle with complex pragmatic analogies.

Neuro-symbolic AI can augment LLMs for better analogy modeling.

The approach maintains efficiency while enhancing explainability.

Abstract

A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning. In this article, we delve into the performance of Large Language Models (LLMs) in dealing with progressively complex analogies expressed in unstructured text. We discuss analogies at four distinct levels of complexity: lexical analogies, syntactic analogies, semantic analogies, and pragmatic analogies. As the analogies become more complex, they require increasingly extensive, diverse knowledge beyond the textual content, unlikely to be found in the lexical co-occurrence statistics that power LLMs. To address this, we discuss the necessity of employing Neuro-symbolic AI techniques that combine statistical and symbolic AI, informing the representation of unstructured text to highlight and augment relevant content, provide abstraction and guide the mapping process. Our knowledge-informed approach maintains the efficiency of LLMs while preserving the ability to explain analogies for pedagogical applications.