在跨语言语言模型中量化对政治家的性别偏见
Karolina Stańczak1, Sagnik Ray Choudhury1, Tiago Pimentel2
1Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
PloS one
|November 28, 2023
概括
大型语言模型在描述七种语言的政治家方面显示了性别偏见. 这种偏差在较大的模型中并不一定更大,这与一些预期相反.
科学领域:
- 自然语言处理自然语言处理.
- 计算语言学 计算语言学
- 社会偏见研究研究
背景情况:
- 大型预训练语言模型 (LPLM) 已被证明反映了其培训数据中存在的社会偏见.
- 了解和量化这些偏见,特别是性别偏见,对于负责任的AI开发至关重要.
研究的目的:
- 引入一种探测LPLM的方法,以研究对政治家的多语言性别偏见.
- 量化LPLM在提到政治家时使用的与性别相关的语言 (形容词和动词).
主要方法:
- 策划了全球25万名政治家的数据集,包括他们的姓名和性别.
- 在七种语言和六种语言建模架构中进行了多语言研究.
- 分析了LPLM在政治人物名字附近生成的形容词和动词的使用情况,按性别分层.
主要成果:
- 预先训练有素的语言模型在不同的语言中表现出对政治家的不同态度.
- "漂亮"和"离婚"等某些术语主要与女性政治家有关.
- 发现"死亡"和"指定"等词与男性和女性政治家有关.
结论:
- 该研究提供了一种在LPLM中进行多语言性别偏见分析的方法.
- 结果表明,在LPLM中存在特定的性别语言关联,因语言而异.
- 与之前的一些研究相反,较大的LPLM并不比较小的LPLM显示出明显更大的性别偏见.
相关概念视频
02:16Stereotype Content Model
14.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.7K
01:27Language and Cognition
352
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.
352
01:22Bias
4.2K
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
4.2K
02:55Stereotypes, Prejudice, and Discrimination
90.2K
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who...
90.2K
01:29Bias in Epidemiological Studies
291
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
291
01:31Confirmation Biases
5.5K
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
5.5K