语言 in vivo vs. in silico:大小很重要,但更大的语言模型仍然无法理解与人类相匹配的语言,原因是难以穿透的语义参考
Vittoria Dentella1, Fritz Günther2, Evelina Leivada3,4
1Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy.
PloS one
|July 17, 2025
概括
大型语言模型 (LLM) 显示,随着大小的增加,性能得到了改善,但在理解语法方面仍然与人类有所不同. 仅靠扩展可能无法完全弥合人工智能和人类认知之间的语言处理差距.
科学领域:
- 计算语言学 计算语言学
- 认知科学 认知科学
- 人工智能的人工智能
背景情况:
- 大型语言模型 (LLM) 越来越复杂,但它们完全复制人类语言理解的能力仍在争论中.
- 在语言任务上,LLM和人类之间的表现差异表明当前AI模型的潜在局限性.
- 模型大小 (缩放) 对这些性能差异的影响需要进一步调查.
研究的目的:
- 调查模型扩展在大型语言模型 (LLM) 中的作用及其对弥合性能差距与人类语言能力的影响.
- 确定增加LLM大小是否可以解释与人类相比,在语言任务中观察到的定性和定量差异.
- 分析LLM对语法敏感性的分析,并将其与人类判断进行比较.
主要方法:
- 三个不同大小的LLM (Bard,ChatGPT-3.5,ChatGPT-4) 在语法判断任务中进行了测试.
- 这项任务包括语言现象,如对焦,中心嵌入,比较和负极性.
- 收集并分析了1200个判断的准确性,稳定性和反复提示后的改进,并对80名人类参与者进行了比较.
主要成果:
- 聊天GPT-4,最大的模型,实现了比人类 (76%) 更高的整体准确性 (80%),但仅在语法句子上表现出色.
- 与人类 (9.6%) 相比,ChatGPT-4在判断中表现出较少的稳定性,答案振荡的可能性更高 (12.5%).
- 尽管在规模上提高了表现,但与人类语言直觉相比,LLM对语法表现出了不同的敏感性.
结论:
- 虽然模型缩放提高了LLM的性能,但它并不能完全复制人类对语法敏感性的敏感性.
- 仅仅是缩放规模不太可能解决LLM和人类处理语言的方式的根本差异.
- 语言学习中的关键差异,包括证据类型,刺激的贫困和语义幻觉,突出了体内和体内语言学习之间的差异.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
587
08:32Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks
Published on: September 5, 2019
5.7K
相关概念视频
Higher Mental Functions of the Brain: Language
1.0K
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...
1.0K
Language and Cognition
450
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.
450
Language Development
455
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...
455
Components of Language
408
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.
408
Improving Translational Accuracy
2.7K
2.7K
