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

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, syntactic, semantic, and pragmatic. 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. We discuss neurosymbolic 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. This maintains the efficiency of LLMs while preserving the ability to explain analogies for pedagogical applications.