人工智能生成内容的偏见:对大型语言模型产生的新闻进行了检查
Xiao Fang1, Shangkun Che2, Minjia Mao3
1University of Delaware, Newark, USA. xfang@udel.edu.
Scientific reports
|March 3, 2024
概括
大型语言模型 (LLM) 产生人工智能生成的内容 (AIGC),但表现出显著的性别和种族偏见. 聊天GPT显示出最少的偏见,并拒绝了有害的提示.
科学领域:
- 人工智能的人工智能
- 自然语言处理自然语言处理.
- 计算社会科学 计算社会科学
背景情况:
- 大型语言模型 (LLM) 越来越多地用于生成人工智能生成内容 (AIGC).
- 了解LLM的局限性,特别是偏见,对于负责任的AI部署至关重要.
- 以前的研究已经突出了人工智能系统的潜在偏见,需要对LLM生成文本进行进一步调查.
研究的目的:
- 调查来自七位著名法学士的AI生成内容 (AIGC) 中存在的性别和种族偏见.
- 为了比较不同LLM的偏差水平,包括ChatGPT和LLaMA.
- 分析LLM对偏见提示的响应,并确定能够拒绝有害内容生成的模型.
主要方法:
- 收集了来自知名来源的新闻文章 (纽约时报,路透社).
- 利用新闻头条作为七个LLM生成AIGC的提示.
- 通过将其与原始文章进行比较,评估了AIGC的性别和种族偏见.
- 将性别偏见的信息引入提示,以进一步评估偏见和模型拒绝能力.
主要成果:
- 所有审查的LLM都产生了AIGC,表现出大量的性别和种族偏见.
- 在大多数LLM输出中,观察到对女性和黑人种族个人的明显歧视.
- 聊天GPT显示了最低的偏差水平,并且是唯一一个在给定偏差提示时下降生成的模型.
结论:
- 当前LLM的AI生成内容具有显著的性别和种族偏见.
- 法律法规需要进一步发展,以减轻偏见,并确保公平的内容生成.
- 聊天GPT拒绝偏见提示的能力表明,朝着更负责任的AI迈出了一步,尽管偏见仍然是一个关键问题.
相关概念视频
01:16Non-equilibrium in the Cell
4.4K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.4K
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
02:28Leaky Scanning
5.1K
During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R...
5.1K
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
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
01:27Language and Cognition
345
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.
345