Human-machine cooperation for semantic feature listing
This work addresses the challenge of automating semantic feature norm generation for researchers in cognitive science and AI, though it appears incremental as it builds on existing LLM methods.
The paper tackles the problem of generating semantic feature norms, which traditionally require extensive human labor, by combining a learned model of human lexical-semantics from limited data with LLM-generated data to efficiently produce high-quality feature norms.
Semantic feature norms, lists of features that concepts do and do not possess, have played a central role in characterizing human conceptual knowledge, but require extensive human labor. Large language models (LLMs) offer a novel avenue for the automatic generation of such feature lists, but are prone to significant error. Here, we present a new method for combining a learned model of human lexical-semantics from limited data with LLM-generated data to efficiently generate high-quality feature norms.