聊天GPT更依赖于辅音而不是元音来识别单词
1Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Spain.
Journal of cognition
|February 18, 2026
概括
像ChatGPT这样的大型语言模型 (LLM) 呈现出类似人类的偏见,在词相似性判断中优先考虑辅音而不是元音. 这表明AI可以无意中从数据中学习人类语言偏见.
科学领域:
- 认知科学 认知科学
- 人工智能的人工智能
- 计算语言学 计算语言学
背景情况:
- 人类语言的获取涉及偏见,比如更多地依赖辅音而不是元音来识别单词.
- 在广泛的数据集上训练的大型语言模型 (LLM) 可以模仿人类语言模式.
- 通过数据规律性跟踪在LLM中出现类似人类偏见需要进行调查.
研究的目的:
- 测试是否跟踪培训数据中的语言规律性足以使LLMs发展辅音偏差.
- 调查人工智能模型在语言处理中是否表现出类似人类的语音偏差.
主要方法:
- 测试了一个假设,关于在LLMs出现辅音偏差.
- 查询了ChatGPT,以比较无意义词的相似性 (有母音与辅音变化) 与目标词的相似性.
- 在英语和西班牙语任务中分析了相似性判断.
主要成果:
- 该研究观察到,在判断单词相似性时,ChatGPT优先考虑辅音而不是元音.
- 这种辅音偏差在英语和西班牙语语言测试中是一致的.
- 这些发现表明,LLM可以复制人类的语音偏差.
结论:
- 追踪自然语言数据集中的规律性可能足以使LLM产生类似人类的偏见,特别是辅音偏见.
- 这项研究表明,人工智能可以无意中学习和复制训练数据中存在的人类认知偏见.
- 需要进一步的研究来探索人工智能学习人类偏见的程度和影响.
更多相关视频
05:38Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
Published on: June 29, 2021
2.9K
09:09Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
912
相关概念视频
Components of Language
839
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.
839
Sign Test for Matched Pairs
434
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in...
To conduct the sign test, we first calculate the differences in...
434
Tip-of-the-Tongue Phenomenon
542
The tip-of-the-tongue (TOT) phenomenon is a cognitive experience characterized by a temporary inability to retrieve specific information from memory despite having a strong feeling of knowing the information. Although individuals cannot access the target word or detail, they frequently recall related elements, such as its initial letter, syllable count, or context. This partial retrieval often causes frustration, as one might recognize a familiar face or know that a name starts with a specific...
542
Detection of Gross Error: The Q Test
7.1K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
7.1K
Language Development
969
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...
969
Complementation Tests
6.3K
A complementation test is a simple cross to identify whether the two mutations are located on the same gene or different genes. It was first performed by Edward Lewis in the 1940s while working on fruit flies. He developed the test to identify the location and arrangement of different mutations on chromosomes.
Organisms heterozygous for different mutations are crossed pairwise in all combinations. If present on different genes, the mutations can complement each other by providing the missing...
Organisms heterozygous for different mutations are crossed pairwise in all combinations. If present on different genes, the mutations can complement each other by providing the missing...
6.3K
