Do large language models solve verbal analogies like children do?

Analogy-making lies at the heart of human cognition. Adults solve analogies such as $\mathit{\text{Horse}}\mathit{\text{belongs}}\mathit{\text{to}}\mathit{\text{stable}}\mathit{\text{like}}\mathit{\text{chicken}}\mathit{\text{belongs}}\mathit{\text{to}}\mathit{\text{...?}}$ by mapping relations ($\mathit{\text{kept}}\mathit{\text{in}}$) and answering $\mathit{\text{chicken}}\mathit{\text{coop}}$. In contrast, children often use association, e.g., answering $\mathit{\text{egg}}$. This paper investigates whether large language models (LLMs) solve verbal analogies in A:B::C:? form using associations, similar to what children do. We use verbal analogies extracted from an online adaptive learning environment, where 14,002 7-12 year-olds from the Netherlands solved 622 analogies in Dutch. The six tested Dutch monolingual and multilingual LLMs performed around the same level as children, with MGPT performing worst, around the 7-year-old level, and XLM-V and GPT-3 the best, slightly above the 11-year-old level. However, when we control for associative processes this picture changes and each model’s performance level drops 1-2 years. Further experiments demonstrate that associative processes often underlie correctly solved analogies. We conclude that the LLMs we tested indeed tend to solve verbal analogies by association with C like children do.