Supplementary material for the article "Child vs. machine language learning: Can the logical structure of human language unleash LLMs?"

This data set includes the supplementary material for the article "Language as a Mirror of the Mind: What can Children Tell Us about Distributivity?". All content is documented in the README.md file.

Abstract: We argue that human language learning proceeds in a manner that is different in nature from current approaches to training LLMs, predicting a difference in learning biases. We then present evidence from German plural formation by LLMs that confirm our hypothesis that even very powerful implementations produce results that miss aspects of the logic inherent to language that humans have no problem with. We conclude that attention to the different structures of human language and artificial neural networks is likely to be an avenue to improve LLM performance.