Using large language models to estimate features of multi-word expressions: Concreteness, valence, arousal
This provides a method for generating psycholinguistic data for multi-word expressions, aiding researchers in stimulus selection, though it is incremental as it applies existing LLMs to a new domain.
The study tackled the problem of estimating psycholinguistic features (concreteness, valence, arousal) for multi-word expressions using large language models, achieving strong correlations with human ratings (e.g., r = .8 for concreteness) and matching or outperforming previous AI models.
This study investigates the potential of large language models (LLMs) to provide accurate estimates of concreteness, valence and arousal for multi-word expressions. Unlike previous artificial intelligence (AI) methods, LLMs can capture the nuanced meanings of multi-word expressions. We systematically evaluated ChatGPT-4o's ability to predict concreteness, valence and arousal. In Study 1, ChatGPT-4o showed strong correlations with human concreteness ratings (r = .8) for multi-word expressions. In Study 2, these findings were repeated for valence and arousal ratings of individual words, matching or outperforming previous AI models. Study 3 extended the prevalence and arousal analysis to multi-word expressions and showed promising results despite the lack of large-scale human benchmarks. These findings highlight the potential of LLMs for generating valuable psycholinguistic data related to multiword expressions. To help researchers with stimulus selection, we provide datasets with AI norms of concreteness, valence and arousal for 126,397 English single words and 63,680 multi-word expressions