为了模拟人类语言预测，让大语言模型不那么超人类
To model human linguistic prediction, make LLMs less superhuman
AI总结：
本文指出大语言模型因超人类预测能力而无法解释人类阅读行为，主张通过模拟人类记忆来改进模型，并提出新实验方向。
摘要：
当我们阅读时，我们会预测即将出现的单词；这些预测会影响我们的阅读行为。大语言模型（LLMs）与人类一样，会对即将出现的单词进行预测，它们的成功促使它们被用作人类语言预测的模型。令人惊讶的是，在过去几年中，随着LLMs预测下一个单词的能力提高，它们解释阅读行为的能力却下降了。我们认为这是因为当前的LLMs预测即将出现的单词的能力远高于人类读者。这种“超人类性”是由LLMs大量的训练数据、对训练示例更强的长期记忆以及更强的短期记忆驱动的。我们主张开发具有类人记忆的LLMs，并进行新的实验来衡量人类与LLMs之间的一致性，并概述了实现这些目标的方向。
英文摘要：
When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs), which, like humans, make predictions about upcoming words, has motivated their use as models of human linguistic prediction. Surprisingly, in the last few years, as LLMs' ability to predict the next word has improved, their ability to explain reading behavior has declined. We argue this is because current LLMs can predict upcoming words much better than human readers can. This 'superhumanness' is driven by LLMs' extensive training data, stronger long-term memory of training examples, and stronger short-term memory. We advocate for LLMs with human-like memory and for new experiments to measure the alignment between humans and LLMs, and outline directions towards achieving these goals.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
