虚幻真实还是单纯曝光？基于LLM的社交媒体模拟中的模型依赖重复效应
Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations
浏览论文内容
中文总结 AI 辅助
本研究在LLM社交媒体模拟中探究虚幻真实效应，发现不同模型表现各异，其中Gemma-3最接近人类行为，警示不可假设统一复现该效应。
中文摘要 AI 辅助
生成式智能体基模型（GABMs）越来越多地被用于模拟社交媒体动态，包括错误信息的传播。为了使此类社会模拟能够有效代理人类行为，LLM智能体应复现已确立的人类认知偏差，其中包括虚幻真实效应（ITE），即重复接触某一主张会增加其感知真实性。我们研究了在社交媒体模拟情境中，ITE是否以及如何在四个LLM（Gemma-3-4b-it、Qwen2.5-7B-Instruct、Llama-3.1-8B-Instruct和GPT-5-nano）中显现。我们提出了一种两阶段上下文内实验设计，将重复操作嵌入到逼真的新闻流交互中。利用该设计，我们收集了336,000个真实性、重要性、情感和兴趣评分，涵盖100条陈述、10种信息流变体和3次重复。关键比较是在模拟阶段反复出现的陈述与在同一实验上下文窗口内评分的完全未见过的陈述之间进行的评分差异。我们区分了真正的ITE（特定于真实性的重复增强）与单纯曝光效应。我们运行了OLS回归，随后使用线性混合效应模型来考虑模型和评分之间的差异。我们的结果揭示了四种性质上不同的模式：Gemma-3表现出真正的ITE；Qwen2.5显示出单纯曝光效应；GPT-5-nano对真实性没有重复效应，并对重复内容表现出轻微怀疑；Llama-3.1在评估维度下降的同时，真实性有小幅提升。关键在于，温度对这些发现没有影响，方差分解突显了LLM评分行为的高度上下文敏感性。我们的研究结果警示不要假设在社交模拟中LLM会统一复现ITE，同时表明Gemma-3-4b-it可能为与错误信息相关的模拟提供最具行为真实性的近似。
英文摘要
Generative agent-based models (GABMs) are increasingly used to simulate social media dynamics, including misinformation spread. For such social simulations to be valid proxies of human behavior, LLM agents should replicate established human cognitive biases, among them the Illusory Truth Effect (ITE), where repeated exposure to a claim increases its perceived truth value. We investigate whether and how the ITE manifests across four LLMs (Gemma-3-4b-it, Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, and GPT-5-nano) in a social media simulation context. We propose a two-phase within-context experimental design that embeds the repetition manipulation inside a realistic news feed interaction. Using this design, we collect 336,000 truth, importance, sentiment, and interest ratings across 100 statements, 10 feed variants, and 3 replications. The key comparison is between ratings assigned to repeated statements, seen throughout a simulation phase, and completely unseen ones, rated within the same experimental context window. We distinguish genuine ITE (truth-specific repetition boost) from mere exposure effects. We run an OLS regression followed by a Linear Mixed-Effect Model to account for differences across models and ratings. Our results reveal four qualitatively distinct patterns: Gemma-3 exhibits a genuine ITE; Qwen2.5 shows a mere exposure effect; GPT-5-nano displays no repetition effect on truth and mild skepticism toward repeated content; Llama-3.1 shows a small truth boost alongside decreases in evaluative dimensions. Crucially, temperature has no effect on these findings, and a variance decomposition highlights the high context-sensitivity of LLM rating behavior. Our findings caution against assuming uniform ITE replication across LLMs in social simulations, while suggesting that Gemma-3-4b-it may offer the most behaviorally realistic approximation for misinformation-related simulations.
发表机构
- University of Zurich（苏黎世大学）
机构由 AI 辅助整理，请以论文原文为准。
