Why Do We Need Neuro-symbolic AI to Model Pragmatic Analogies?
This work addresses the challenge of improving AI's analogical reasoning for educational and interpretability purposes, though it appears incremental as it builds on existing neuro-symbolic methods.
The paper investigates the limitations of Large Language Models (LLMs) in handling complex analogies, particularly pragmatic ones that require extensive external knowledge beyond text statistics, and proposes neuro-symbolic AI as a solution to enhance performance while maintaining explainability for pedagogical use.
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.