大型语言模型的文化偏见和文化对齐
Yan Tao1, Olga Viberg2, Ryan S Baker3
1Department of Information Science, Cornell University, Ithaca, NY 14853, USA.
PNAS nexus
|September 18, 2024
概括
生成性AI模型显示文化偏见,偏好西方价值观. 文化促使可以改善AI.
科学领域:
- 人工智能的人工智能
- 社会学 社会学 社会学
- 人与计算机的交互
背景情况:
- 文化显著影响人类的推理,行为和沟通.
- 越来越多的人工智能 (人工智能) 的使用在任务中引发了人们对嵌入式文化价值观和潜在偏见的担忧.
- 人工智能模型可能无意中促进某些文化,并影响真实的表达.
研究的目的:
- 评估广泛使用的大型语言模型 (LLM) 中的文化偏见.
- 评估文化诱导作为减轻偏见的策略的有效性.
主要方法:
- 对五个OpenAI大型语言模型 (GPT-4o,GPT-4-turbo,GPT-4,GPT-3.5-turbo,GPT-3) 的分类评估.
- 模型响应与全国代表性调查数据的比较.
- 测试文化提示,以提高国家特定的AI输出对齐.
主要成果:
- 所有评估的LLM都表现出与英语和新教欧洲国家的文化价值观一致.
- 在后来的模型 (GPT-4系列) 中,文化诱导改善了71-81%的国家/地区的AI输出的文化调整.
结论:
- 生成型人工智能模型目前表现出显著的文化偏见.
- 文化促使是一种可行的策略,可以增加AI的文化对齐.
- 建议进行持续的评估和文化提示,以减少生成AI的偏见.
相关概念视频
Language and Cognition
336
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.
336
Stereotype Content Model
14.0K
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...
14.0K
Improving Translational Accuracy
9.4K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.4K
Bias
3.8K
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...
3.8K
Confirmation 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
Cultural Influences on Personality
132
Individualist and collectivist cultures emphasize different core values, shaping personality in distinct ways. In individualist cultures, such as those in the United States, England, and Australia, people prioritize independence, competition, and personal achievement. These societies tend to promote self-focused traits, with individuals often reporting higher levels of self-esteem. In contrast, collectivist cultures, commonly found in regions like Asia, Africa, and South America, emphasize...
132


