Kaye Nikki G, Gordon Peter C
Department of Psychology & Neuroscience, The University of North Carolina at Chapel Hill, CB#3270, Chapel Hill, NC, 26599-3270, USA.
Psychon Bull Rev. 2025 Aug 13. doi: 10.3758/s13423-025-02756-9.
Online measures of reading have been studied with the goal of understanding how humans process language incrementally as they progress through a text. A focus of this research has been on pinpointing how the context of a word influences its processing. Quantitatively measuring the effects of context has proven difficult but with advances in artificial intelligence, large language models (LLMs) are more capable of generating humanlike language, drawing solely on information about the probabilistic relationships of units of language (e.g., words) occurring together. LLMs can be used to estimate the probability of any word in the model's vocabulary occurring as the next word in a given context. These next-word probabilities can be used in the calculation of information theoretic metrics, such as entropy and surprisal, which can be assessed as measures of word-by-word processing load. This is done by analyzing whether entropy and surprisal derived from language models predict variance in online measures of human reading comprehension (e.g., eye-movement, self-paced reading, ERP data). The present review synthesizes empirical findings on this topic and evaluates their methodological and theoretical implications.
对在线阅读测量进行了研究，目的是了解人类在阅读文本过程中如何逐步处理语言。这项研究的一个重点是确定单词的上下文如何影响其处理过程。事实证明，定量测量上下文的影响很困难，但随着人工智能的发展，大型语言模型（LLMs）更有能力生成类人语言，仅依靠关于一起出现的语言单位（如单词）的概率关系的信息。大型语言模型可用于估计模型词汇表中任何单词在给定上下文中作为下一个单词出现的概率。这些下一个单词的概率可用于计算信息理论指标，如熵和意外性，它们可作为逐词处理负荷的度量进行评估。这是通过分析语言模型得出的熵和意外性是否能预测人类阅读理解的在线测量（如眼动、自定步速阅读、ERP数据）中的差异来实现的。本综述综合了关于该主题的实证研究结果，并评估了它们的方法学和理论意义。
