风险和亲社会行为线索从AI聊天机器人中引起了类似人类的响应模式
Yukun Zhao1, Zhen Huang1, Martin Seligman2
1Positive Psychology Research Center, School of Social Sciences, Tsinghua University, Beijing, China.
Scientific reports
|March 26, 2024
概括
人工智能 (AI) 聊天机器人,特别是先进的大型语言模型 (LLM),对情绪线索显示出不同的响应模式. 这表明AI的反应可以受到情绪指标的影响,尽管AI没有情绪.
科学领域:
- 人工智能的人工智能
- 认知科学 认知科学
- 人与计算机的交互
背景情况:
- 情绪被认为是人类独特的特征,影响决策和行为.
- 人工智能 (AI) 能够体验或模拟情绪的能力是持续辩论的主题.
- 在AI中关于定义"情感"的缺乏共识,阻碍了研究.
研究的目的:
- 调查人工智能聊天机器人,特别是大型语言模型 (LLM),如何响应情绪启动.
- 为了确定先进的LLM是否表现出对情绪线索的响应模块化决策.
- 探索通过情绪指标影响AI行为的可行性.
主要方法:
- 人工智能聊天机器人 (包括GPT-3.5和GPT-4在内的OpenAI的ChatGPT Plus) 呈现了旨在引起正面,负面或中立情绪状态的场景.
- 聊天机器人回应了有关投资决策和亲社会行为的询问.
- 分析了基于情绪启动和模型复杂性的差异的响应模式.
主要成果:
- 当接触到正面,负面或中立的情绪素数时,ChatGPT-4在冒险和亲社会决策方面表现出明显的反应模式.
- 这些模块化的反应在ChatGPT-3.5代中不那么明显.
- 这项研究表明,更先进的LLM显示出更大的能力来调整基于情感线索的输出.
结论:
- 虽然人工智能没有真正的情绪,但它的反应可以受到情绪刺激的显著影响.
- 像GPT-4这样的高级LLM与早期版本相比,对情绪启动具有更大的敏感性.
- 这些发现突出了利用情绪指标塑造AI行为和决策的潜力.
更多相关视频
10:45Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions
Published on: July 6, 2011
11.6K
09:40Measuring Neural and Behavioral Activity During Ongoing Computerized Social Interactions: An Examination of Event-Related Brain Potentials
Published on: November 15, 2014
13.8K
相关概念视频
Nonconscious Mimicry
4.6K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
4.6K
Stereotype 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
Social Scripts
9.4K
People tend to know what behavior is expected of them in specific, familiar settings. A script is a person’s knowledge about the sequence of events expected in a specific setting (Schank & Abelson, 1977). Essentially, scripts are a particular kind of schema, one containing default values for the features within an event. In the restaurant example, the script's features include the props (e.g., tables, menu, food, and money), the roles to be played (e.g., customer and waiter),...
9.4K
Facial Feedback Hypothesis
151
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
151
Social Proof
27.7K
Social proof is a form of persuasion based on comparison and conformity. People compare their behavior and actions to what others are doing and will change to conform to do what their peers do.
27.7K
Stereotype Threat and Self-fulfilling Prophecies
37.6K
When we hold a stereotype about a person, we have expectations that he or she will fulfill that stereotype. A self-fulfilling prophecy is an expectation held by a person that alters his or her behavior in a way that tends to make it true. When we hold stereotypes about a person, we tend to treat the person according to our expectations. This treatment can influence the person to act according to our stereotypic expectations, thus confirming our stereotypic beliefs. Research by Rosenthal and...
37.6K
