Semantic Feature Verification in FLAN-T5
This work enhances traditional methods for cognitive scientists by improving semantic feature norm verification, with implications for understanding conceptual representation in humans and machines, though it is incremental as it builds on existing human-generated datasets.
The study tackled the problem of generating semantic feature norms for evaluating conceptual structure by using a large language model to verify norms, showing that machine-verified norms capture additional aspects of conceptual structure and better explain human judgments of semantic similarity for distally related items.
This study evaluates the potential of a large language model for aiding in generation of semantic feature norms - a critical tool for evaluating conceptual structure in cognitive science. Building from an existing human-generated dataset, we show that machine-verified norms capture aspects of conceptual structure beyond what is expressed in human norms alone, and better explain human judgments of semantic similarity amongst items that are distally related. The results suggest that LLMs can greatly enhance traditional methods of semantic feature norm verification, with implications for our understanding of conceptual representation in humans and machines.