在人类和大型语言模型中积极使用潜在树结构句子表示
Wei Liu1, Ming Xiang2, Nai Ding3,4
1Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Sciences, Zhejiang University, Hangzhou, China.
Nature human behaviour
|September 10, 2025
概括
人类和大型语言模型 (LLM) 都使用底层树结构来表示句子. 这项研究表明,像人类一样,LLM编码句子组成部分,揭示了共享的认知和计算原则.
科学领域:
- 认知科学 认知科学
- 计算语言学 计算语言学
- 神经科学是一个神经科学.
背景情况:
- 了解人类大脑和大型语言模型 (LLM) 中的句子表示是一个关键的挑战.
- 研究人类认知和人工智能之间的共同机制对于推进这两个领域至关重要.
研究的目的:
- 调查人类和LLM是否在句子中编码树结构组成部分.
- 为了比较人类和LLM之间的句子处理策略,使用一种新的一次性学习任务.
主要方法:
- 一次性学习任务旨在评估句子处理中的组成部分删除.
- 参与者 (N=372,母语是中文,英语或双语) 和LLM (例如,ChatGPT) 执行了这个任务.
- 分析的重点是单词删除模式是否反映了组成结构,而不是单词属性或位置.
主要成果:
- 人类参与者和LLM都优先删除组成部分,而不是非组成部分的字符串.
- 删除模式遵循中文和英语的语言特定规则.
- 根据删除的字符串,重建底层的选区树结构是成功的.
结论:
- 隐藏的树结构句子表示表现出现在人类和LLMs.
- 这些发现表明生物和人工系统如何处理语言语法中的共享原则.
- 结果挑战了仅依赖单词属性和句子理解位置的模型.
相关概念视频
Language Development
855
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...
855
Language and Cognition
716
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.
716
Components of Language
760
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.
760
Language
890
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
890
Higher Mental Functions of the Brain: Language
3.5K
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
3.5K
Genetic Lingo
113.9K
Overview
113.9K
