类似人类的直观行为和推理偏见出现在大型语言模型中,但在ChatGPT中消失了
Thilo Hagendorff1, Sarah Fabi2, Michal Kosinski3
1University of Stuttgart, Stuttgart, Germany.
Nature computational science
|January 4, 2024
概括
大型语言模型 (LLM) 呈现出类似人类的直观思维和错误,随着它们的成长. 然而,新的ChatGPT模型避免了这些认知陷,显示了先进的推理能力.
科学领域:
- 认知科学 认知科学
- 人工智能的人工智能
- 自然语言处理自然语言处理.
背景情况:
- 认知反射测试和语义幻觉揭示了人类的直观 (系统1) 和深思熟虑 (系统2) 思维.
- 以前的研究主要集中在人类的认知偏见和决策过程.
研究的目的:
- 调查大型语言模型 (LLM) 是否表现出类似人类的认知偏见.
- 评估OpenAI的生成预训练变压器模型的推理能力,包括ChatGPT.
- 用心理学方法来探索LLM中的新兴特征.
主要方法:
- 对各种OpenAI模型进行了一系列语义错觉和认知反射测试.
- 对比了不同型号尺寸和版本的性能,包括ChatGPT-3.5和ChatGPT-4.
- 分析了模型对直观错误和思维链推理模式的反应.
主要成果:
- 较小和较不熟练的LLM显示出类似人类的直觉思维和认知错误.
- 聊天GPT模型 (3.5和4) 始终避免认知陷,并作出正确的反应.
- 聊天GPT模型使用了思维链推理,但即使受到限制,也保持了准确性,这表明了系统1处理的改进.
结论:
- 法学士课程的发展显示出向更准确,更类似人类推理的进展,ChatGPT模型显示出了显著的飞跃.
- 心理测试框架对于揭示先进人工智能的新兴特性和认知行为是有价值的.
- 这些发现表明,在先进的LLM中,下一个词的生成比早期的模型更强大.
相关概念视频
01:27Language and Cognition
348
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.
348
01:20Introduction to Cognitive Psychology
490
Cognitive psychology is the field of psychology dedicated to examining how people think. It attempts to explain how and why we think the way we do by studying the interactions among human thinking, emotion, creativity, language, and problem-solving, as well as other cognitive processes. Cognitive psychology studies how information is processed and manipulated in remembering, thinking, and knowing.
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
490
01:37Reason and Intuition
6.5K
The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...
6.5K
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
01:13Nonconscious Mimicry
4.6K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
4.6K
01:22Language Development
368
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...
368