研究不同人群在与大模型互动中受虚假信息影响的差异。
Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions
- 用人类立场数据和大模型生成论据，分析双向说服机制。
- 发现大模型对虚假信息的敏感度与人类群体特征一致。
- 多智能体模拟显示大模型也会形成信息回音室。
现有虚假信息暴露与易感性挑战在不同人口群体间存在差异，部分群体更易受影响。大语言模型（LLMs）通过大规模生成有说服力的内容并强化既有偏见，引入了新维度。本研究探究人类与大模型在接触虚假信息时的双向说服动态。我们利用人类立场数据集分析人类对大模型的影响，并通过生成大模型驱动的说服性论据评估大模型对人类的影响。此外，采用多智能体大模型框架分析基于人口特征的大模型代理间说服导致的虚假信息传播。结果表明，人口因素会影响大模型对虚假信息的易感性，其模式与人类群体中的易感性模式高度一致。同时发现，如同人类群体，多智能体大模型也表现出回音室行为。该研究揭示了人类与大模型在虚假信息情境下的相互作用，强调了人口差异的重要性，并为未来干预措施提供洞见。
原文摘要 · Abstract (English)
Existing challenges in misinformation exposure and susceptibility vary across demographic groups, as some populations are more vulnerable to misinformation than others. Large language models (LLMs) introduce new dimensions to these challenges through their ability to generate persuasive content at scale and reinforcing existing biases. This study investigates the bidirectional persuasion dynamics between LLMs and humans when exposed to misinformative content. We analyze human-to-LLM influence using human-stance datasets and assess LLM-to-human influence by generating LLM-based persuasive arguments. Additionally, we use a multi-agent LLM framework to analyze the spread of misinformation under persuasion among demographic-oriented LLM agents. Our findings show that demographic factors influence susceptibility to misinformation in LLMs, closely reflecting the demographic-based patterns seen in human susceptibility. We also find that, similar to human demographic groups, multi-agent LLMs exhibit echo chamber behavior. This research explores the interplay between humans and LLMs, highlighting demographic differences in the context of misinformation and offering insights for future interventions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。