人类语言学习逻辑可启发大模型性能提升
Child vs. machine language learning: Can the logical structure of human language unleash LLMs?
- 对比人类语言习得与当前大模型训练差异，提出学习偏置不同
- 德语复数形式实验显示大模型遗漏人类自然掌握的语言逻辑
- 强调语言结构与神经网络差异对模型改进的关键意义
我们认为人类语言学习的本质不同于当前大模型的训练方式，预测两者存在不同的学习偏置。通过德语复数形态的实验证据表明，即使是最强大的大模型也未能捕捉人类轻易掌握的语言内在逻辑。研究结论指出，关注人类语言结构与人工神经网络之间的本质差异，或将成为提升大模型表现的重要路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。