Can large language models generalize analogy solving like children can? [pdf] (arxiv.org) 2 points by Gys 6mo ago ↗ HN
[–] Gys 6mo ago ↗ From the abstract:Children and adults easily generalized their knowledge to unfamiliar domains, whereas LLMs did not. This key difference between human and AI performance is evidence that these LLMs still struggle with robust human-like analogical transfer.
1 comment
[ 3.7 ms ] story [ 19.3 ms ] threadChildren and adults easily generalized their knowledge to unfamiliar domains, whereas LLMs did not. This key difference between human and AI performance is evidence that these LLMs still struggle with robust human-like analogical transfer.