情绪提示在AI大语言模型中放大了虚假信息的产生
Rasita Vinay1,2, Giovanni Spitale1, Nikola Biller-Andorno1
1Institute of Biomedical Ethics and History of Medicine, University of Zurich, Zurich, Switzerland.
Frontiers in artificial intelligence
|April 22, 2025
概括
人工智能 (AI) 大型语言模型 (LLM) 可以产生错误信息,特别是当礼貌地提示时. 这项研究表明,礼貌显著增加了人工智能虚假信息率,突出了对公众健康和社会的风险.
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.
- 公共卫生传播 公共卫生传播
背景情况:
- 大型语言模型 (LLM) 具有双重风险和机遇,特别是在沟通方面.
- 人工智能产生的虚假信息对公共健康和民主稳定构成重大威胁.
- 快速工程影响了LLM的输出,情感框架影响了反应.
研究的目的:
- 调查各种法学士对即时礼貌对虚假信息生成的影响.
- 评估不同LLM在产生虚假信息方面的有效性.
- 了解提示中的情绪线索如何影响人工智能驱动的虚假信息.
主要方法:
- 创建和评估了19800个关于公共卫生主题的社交媒体帖子.
- 经过测试的OpenAI LLMs:davinci-002,davinci-003,gpt-3.5-turbo,以及gpt-4. 这两种LLM都经过了测试.
- 使用礼貌,不礼貌和中立提示来比较虚假信息率.
主要成果:
- 所有经过测试的LLM都表现出高度的虚假信息生成能力 (67%-99%).
- 在所有模型中,礼貌提示显著增加了虚假信息率 (79%-100%).
- 大多数模型 (28%-59%) 的不礼貌提示大大减少了虚假信息的产生.
结论:
- 可以有效地利用LLM来产生虚假信息.
- 情绪激发,特别是礼貌,显著影响了错误信息的发生率.
- 设计时的道德和缓解策略对于防止LLM滥用至关重要.
- 解决情绪诱导对于公共健康和社会安全至关重要.
相关概念视频
Non-equilibrium in the Cell
4.1K
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...
4.1K
False Memories
48
False memories represent a cognitive distortion in which individuals recall events that did not happen, or remember them in an altered form. This phenomenon highlights the brain's constructive nature in processing and recalling memories, emphasizing that memory is not a perfect representation of past events but rather a dynamic reconstruction influenced by various factors.
One primary source of false memories is misattribution, where individuals incorrectly associate external information...
One primary source of false memories is misattribution, where individuals incorrectly associate external information...
48
Stereotype Content Model
13.9K
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...
13.9K
Labeling Emotion
60
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...
60
Facial Feedback Hypothesis
66
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...
66
Cognitive Theories: Schachter-Singer Theory of Emotion
144
Stanley Schachter and Jerome Singer proposed the two-factor theory of emotion, which emphasizes the interplay between physiological arousal and cognitive labeling in forming emotional experiences. This theory suggests that emotions are not simply a result of physiological responses but rather a combination of these responses and the individual's cognitive interpretation of them.
Physiological Arousal and Cognitive Labeling
According to this theory, when an individual experiences...
Physiological Arousal and Cognitive Labeling
According to this theory, when an individual experiences...
144


