一项对荷兰大型语言模型在句子,段落和书籍阅读中的意外估计的系统评估
1Department of Experimental Psychology, Ghent University, Ghent, Belgium. Sam.Boeve@UGent.be.
Behavior research methods
|August 18, 2025
概括
荷兰大语言模型 (LLM) 被评估其预测阅读时间的能力,支持惊喜理论. GPT-2模型表现最好,显示较小的模型更好地预测阅读困难.
科学领域:
- 心理语言学 心理语言学
- 计算语言学 计算语言学
- 认知科学 认知科学
背景情况:
- 惊喜理论假设阅读困难与单词可预测性线性相关.
- 之前的研究通过语言模型的计算估计在英语中确定了这一效应.
- 许多语言特异模型缺乏对其惊喜估计的心理测量验证.
研究的目的:
- 系统地评估荷兰大语言模型 (LLM) 对于它们的意外估计.
- 评估这些LLM在不同荷兰公司的阅读时间预测得有多好.
- 将荷兰LLMs与多语言模型和N-gram模型进行比较.
主要方法:
- 评估了多个荷兰特定的LLM和多语言模型.
- 从这些模型中使用计算方法估计了word surprisal.
- 与实际阅读时间相关的意外估计来自句子,段落和书籍体.
- 使用诸如"适合性"等指标来比较模型性能.
主要成果:
- 基于GPT-2的荷兰LLMs在预测阅读时间方面表现优异.
- 观察到一个一致的反向缩放趋势:较小模型的意外估计与较大的模型的阅读时间更好地匹配.
- 惊喜对阅读时间的线性效应被复制为荷兰语,尽管依赖于语料库.
结论:
- 荷兰LLM为心理语言学研究提供了宝贵的资源,提供了心理测量排行榜.
- 这些发现挑战了心理语言学普遍语言模型的想法,强调体和模型大小效应.
- 意外估计和提取代码是公开的,以便进一步研究.
更多相关视频
05:22Dissociation of the Confounding Influences of Expectancy and Integrative Difficulty Residing in Anomalous Sentences in Event-related Potential Studies
Published on: May 9, 2019
5.4K
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
681
相关概念视频
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
1.5K
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
1.5K
Components of Language
840
Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs.
840
Language Development
1.1K
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
1.1K
Language and Cognition
881
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
881
