按年被提到
20242025 · 2 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2411.02348 · cs.AI

Can Large Language Models generalize analogy solving like children can?

Claire E. Stevenson, Alexandra Pafford, Han L. J. van der Maas, Melanie Mitchell · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2024-11-05 · 最近 2025-12-18
3不同的人
2活跃月份
3讨论串
6被引(OpenAlex)
arXiv 摘要(候选层不写导读)

In people, the ability to solve analogies such as "body : feet :: table : ?" emerges in childhood, and appears to transfer easily to other domains, such as the visual domain "( : ) :: < : ?". Recent research shows that large language models (LLMs) can solve various forms of analogies. However, can LLMs generalize analogy solving to new domains like people can? To investigate this, we had children, adults, and LLMs solve a series of letter-string analogies (e.g., a b : a c :: j k : ?) in the Latin alphabet, in a near transfer domain (Greek alphabet), and a far transfer domain (list of symbols). 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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论gus_massa · 2025-12

“Preprint: https://arxiv.org/pdf/2411.02348 > For children, the interface was explained and demonstrated in person. Participants then solved two simple practice items without feedback (used to ensure understanding of task). I'm still not sure if the prompt for children is equivalent to the prompt for AI. Anyway, it's hard for the current AI to do these t…”

An 8-year-old defeats AI原评论 ↗
被提交为 story · 2 次