Resumen de Combining the power of large language models with finetuning based on strategically collected human ratings: A case study about age-of-acquisition estimates of Spanish words

Eneko Sendín, Francisco Javier Conde González, Pedro Reviriego, Juan Haro, Pilar Ferré Romeu, José Antonio Hinojosa Poveda, Marc Brysbaert

• This study examined the ability of a large language model, GPT-4o mini, to predict age of acquisition (AoA) for Spanish words, as compared to human ratings. We found a strong correlation (ρ=.75) between the model’s AoA estimates and mean human ratings. This correlation was lower than the level of agreement observed between individual human raters (ρ=.85), but we found that finetuning the model on a relatively small dataset of 2000 human AoA ratings has the potential to enhance the model’s performance to a level comparable to human consensus. Consistent with theoretical expectations, our analyses confirmed that AoA estimates are meaningful only for words within an individual’s vocabulary. Finally, we present a novel dataset of AoA estimates for 28,453 Spanish words likely known by adult speakers.