Garden Path Sentence

Garden-path sentences, which initially lead to an incorrect interpretation before requiring reanalysis, are a key tool for understanding human language processing. Current research uses large language models (LLMs) to investigate how these models handle the ambiguity inherent in such sentences, comparing their performance to human comprehension and exploring the role of syntactic and semantic cues in resolving the ambiguity. This work aims to improve our understanding of how both humans and artificial intelligence process complex linguistic structures, potentially leading to advancements in natural language processing and cognitive science.