Using Analogical Reasoning to Prompt LLMs for Their Intuitions of Abstract Spatial Schemas
MCML Authors
Philipp Wicke
Dr.
Lea Hirlimann
Abstract
Philipp Wicke
Dr.
Lea Hirlimann
Abstract
Abstract notions are often comprehended through analogies, wherein there exists correspondence or partial similarity with more concrete concepts. A fundamental aspect of human cognition involves synthesising embodied experiences into spatial schemas, which profoundly influence conceptualisation and underlie language acquisition. Recent studies have demonstrated that Large Language Models (LLMs) exhibit certain spatial intuitions akin to human language. For instance, both humans and LLMs tend to associate ↑ with hope more readily than with warn. However, the nuanced partial similarities between concrete (e.g., ↑) and abstract (e.g., hope) concepts, remain insufficiently explored. Therefore, we propose a novel methodology utilising analogical reasoning to elucidate these associations and examine whether LLMs adjust their associations in response to analogy-prompts. We find that analogy-prompting is slightly increasing agreement with human choices and the answers given by models include valid explanations supported by analogies, even when in disagreement with human results.
inproceedings
Analogy-ANGLE 2024 @IJCAI 2024
1st Workshop on Analogical Abstraction in Cognition, Perception, and Languageat the 33rd International Joint Conference on Artificial Intelligence. Jeju, Korea, Aug 03-09, 2024.Authors
P. Wicke • L. Hirlimann • J. M. CunhaLinks
PDFResearch Area
BibTeXKey: WHC24