近期两篇arXiv论文探讨了大型语言模型（LLMs）的类比生成能力。第一篇论文提出，LLMs支持类比的平行四边形理论，在生成符合该几何模型的类比方面表现优于人类。然而，第二篇论文揭示了LLM生成的类比在多样性方面存在令人担忧的不足，常常导致领域同质化，并在多样性和质量之间存在权衡。该研究还指出了LLMs处理类比多样性相关信息方式的差异。 AI
影响 突显了LLMs在支持类比等复杂认知任务方面的潜力，以及它们在多样性和质量方面存在的局限性。
排序理由 两篇发表在arXiv上的学术论文，探讨了LLM的能力。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2603.19066v2 Announce Type: replace-cross Abstract: Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D. Recent work suggests that this model poorly captures how humans produce analogies, with simpl…
arXiv:2608.03233v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cognitive capability that drives novelty and creativity. While prior research has extensively investigated the applications and underlyin…
Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cognitive capability that drives novelty and creativity. While prior research has extensively investigated the applications and underlying mechanisms of LLM-based analogy making, its ou…