叙述中的交叉偏差是由生成语言模型的开放式提示产生的
Evan Shieh1, Faye-Marie Vassel2, Cassidy R Sugimoto3
1Young Data Scientists League, Bellevue, WA, USA. evan.shieh@youngdatascientists.org.
Nature communications
|January 8, 2026
概括
生成性语言模型可能会表现出偏见,在开放式提示中省略或将少数群体归属. 这项研究强调了需要制定法规,以确保负责任的人工智能创新和消费者保护.
科学领域:
- 人工智能的人工智能
- 社会科学 社会科学 社会科学
- 计算语言学 计算语言学
背景情况:
- 生成性语言模型 (GLM) 正在迅速部署,引发了人们对影响不同消费者的社会偏见的担忧.
- 现有的关于GLM偏见的研究经常使用明确的身份提示,忽视自然主义用例中的偏见.
- 之前的研究表明,语言技术中的歧视可能在没有明确的身份条款的情况下发生.
研究的目的:
- 通过使用开放式提示,在自由放任的环境中调查GLM的社会偏见.
- 分析GLM产生的输出中的少数身份的代表性和角色.
- 在GLM输出中识别可能对消费者有害的刻板印象模式.
主要方法:
- 来自五个公开的GLM (ChatGPT 3.5,ChatGPT 4,Claude 2.0,Llama 2,PaLM 2) 的基准模型的50万个观测结果的分析.
- 利用开放式提示来模拟自然使用情况 (laissez-faire环境).
- 与少数群体的美国人口普查数据比较生成的输出代表性和角色.
主要成果:
- 与美国人口普查数据相比,GLM输出更有可能省略具有少数种族,性别和/或性取向身份的角色.
- 少数族裔身份往往被降级为下属角色,而不是在生成内容中占主导地位.
- 在GLM输出中观察到的刻板印象模式,可能会不成比例地影响少数群体的个人.
结论:
- 在自由放任的环境中,GLMs表现出偏见,低于代表和刻板印象的少数群体.
- 迫切需要制定法规来指导负责任的AI创新,并减轻偏见的GLMs对消费者的伤害.
- 调查结果强调了在自然环境中评估GLM的重要性,以揭示微妙的歧视形式.
相关概念视频
Stereotype Content Model
15.3K
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...
15.3K
Language Development
831
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...
831
Genetic Lingo
113.7K
Overview
113.7K
Motivational Bias
306
Cognitive bias results from limitations in thinking and information processing, leading to systematic errors in judgment. Conversely, motivational bias stems from personal desires or emotions, causing distortions in perception to align with self-interest. Motivational bias influences how individuals perceive and attribute causes to events, often shaped by personal needs, goals, and self-esteem preservation. This bias can distort judgment, leading to inaccurate assessments of success, failure,...
306
Stereotypes, Prejudice, and Discrimination
94.9K
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...
94.9K
Surveys
16.6K
Often, psychologists develop surveys as a means of gathering data. Surveys are lists of questions to be answered by research participants, and can be delivered as paper-and-pencil questionnaires, administered electronically, or conducted verbally. Generally, the survey itself can be completed in a short time, and the ease of administering a survey makes it easy to collect data from a large number of people.
16.6K

