Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations

2026-09-28

AI Summary

This study investigates whether large language models (LLMs) replicate the human illusory truth effect in social media simulations and how to disentangle genuine belief bias induced by repeated exposure from mere familiarity. Employing generative agent-based modeling, we design a two-stage news feed experiment embedded within authentic interaction contexts, combining OLS regression with linear mixed-effects models to systematically evaluate the truth judgments of four LLMs regarding repeated claims. This work effectively isolates the illusory truth effect from the mere exposure effect, revealing heterogeneous cognitive biases across LLMs. Notably, only Gemma-3 exhibits a genuine individual treatment effect that remains robust against temperature parameter variations, providing empirical support for its suitability as an optimal agent for simulating misinformation propagation.

Abstract

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.

Problem

• Illusory Truth Effect
• Large Language Models
• Social Media Simulation
• Generative Agent-Based Models
• Misinformation

Innovation

• Illusory Truth Effect
• Generative Agent-Based Models
• Within-Context Experimental Design
• Mere Exposure Effect
• Linear Mixed-Effect Model