关于GPT-4的对话性说服力
Francesco Salvi1,2, Manoel Horta Ribeiro3, Riccardo Gallotti4
1EPFL, Lausanne, Switzerland. francesco.salvi@epfl.ch.
Nature human behaviour
|May 19, 2025
概括
大型语言模型 (LLM) 可以个性化论证,显著提高其说服力. 这项研究表明,使用个人数据的人工智能在辩论中比人类更有说服力,这对在线平台有影响.
科学领域:
- 人工智能的人工智能
- 人与计算机的交互
- 计算社会科学 计算社会科学
背景情况:
- 大型语言模型 (LLM) 展示了在产生有说服力的内容方面的能力.
- 有限证据表明,LLM能够根据个体属性来个性化论证,这是评估滥用潜力的关键因素.
研究的目的:
- 调查大语言模型 (LLM) 可以将参数个性化为单个属性的程度.
- 为了比较人类辩论者与GPT-4的说服能力,无论是否访问参与者数据.
主要方法:
- 一项预先注册的研究,涉及900名参与者进行了短暂的多轮辩论.
- 一个2x2x3的因数设计,检查人类与GPT-4对手,有/没有社会人口统计数据访问,以及低/中/高意见强度主题.
- 随机分配到12个实验条件中的1个.
主要成果:
- 当人工智能和人类在说服力上有所不同时,具有个性化的GPT-4在64.4%的时间里更具说服力.
- 个性化GPT-4显示,与非个性化或人类对手相比,辩论后达成更高协议的几率相对增加了81.2%.
- 在P值<0.01和95%置信区间为 [+26.0%, +160.7%]的情况下,统计学显著性得到实现.
结论:
- 大型语言模型,特别是当与个人数据个性化时,表现出显著的说服力.
- 调查结果强调,在设计和管理在线平台时,需要仔细考虑LLM能力,以减轻潜在的滥用.
- 该研究强调了人工智能驱动的沟通在塑造意见和协议方面日益增长的影响.
相关概念视频
Routes of Persuasion
63.5K
Persuasion is the process of changing our attitude toward something based on some kind of communication. Much of the persuasion we experience comes from outside forces. How do people convince others to change their attitudes, beliefs, and behaviors? What communications do you receive that attempt to persuade you to change your attitudes, beliefs, and behaviors?
63.5K
Persuasion Strategies
38.2K
Researchers have tested many persuasion strategies, including the foot-in-the door and the door-in-the-face techniques, in a variety of contexts. Ultimately, the principles are effective in selling products and changing people’s attitude, ideas, and behaviors (Cialdini & Goldstein, 2004).
38.2K
Social Proof
27.3K
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.
27.3K
Group Polarization
34.0K
Group polarization is the strengthening of an original group attitude following the discussion of views within a group (Teger & Pruitt, 1967). That is, if a group initially favors a viewpoint, after discussion the group consensus is likely a stronger endorsement of the viewpoint. Conversely, if the group was initially opposed to a viewpoint, group discussion would likely lead to stronger opposition.
34.0K
The Representativeness Heuristic
15.7K
The representative heuristic describes a biased way of thinking, in which you unintentionally stereotype someone or something. For example, you may assume that your professors spend their free time reading books and engaging in intellectual conversation, because the idea of them spending their time playing volleyball or visiting an amusement park does not fit in with your stereotypes of professors.
15.7K
Confirmation Biases
5.4K
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?
5.4K


