Guardado en:
Detalles Bibliográficos
Autores principales: Martínez, Gonzalo, Molero, Juan Diego, González, Sandra, Conde, Javier, Brysbaert, Marc, Reviriego, Pedro
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2408.16012
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910581244559360
author Martínez, Gonzalo
Molero, Juan Diego
González, Sandra
Conde, Javier
Brysbaert, Marc
Reviriego, Pedro
author_facet Martínez, Gonzalo
Molero, Juan Diego
González, Sandra
Conde, Javier
Brysbaert, Marc
Reviriego, Pedro
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2408_16012
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using large language models to estimate features of multi-word expressions: Concreteness, valence, arousal
Martínez, Gonzalo
Molero, Juan Diego
González, Sandra
Conde, Javier
Brysbaert, Marc
Reviriego, Pedro
Computation and Language
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
title Using large language models to estimate features of multi-word expressions: Concreteness, valence, arousal
topic Computation and Language
url https://arxiv.org/abs/2408.16012