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

arXiv: https://arxiv.org/abs/2609.36278 · HTML: https://mlsanity.com/paper/2609.36278/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms](https://mlsanity.com/paper/2310.05984/) (2023)
- [SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors](https://mlsanity.com/paper/2510.17516/) (2025)
- [Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations](https://mlsanity.com/paper/2504.03274/) (2025)
- [Accumulating Context Changes the Beliefs of Language Models](https://mlsanity.com/paper/2511.01805/) (2025)
- [Agent-Based Modelling Meets Generative AI in Social Network Simulations](https://mlsanity.com/paper/2411.16031/) (2024)
- [Emergence of Scale-Free Networks in Social Interactions among Large Language Models](https://mlsanity.com/paper/2312.06619/) (2023)
- [Understanding Knowledge Drift in LLMs through Misinformation](https://mlsanity.com/paper/2409.07085/) (2024)
- [Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?](https://mlsanity.com/paper/2502.05919/) (2025)
- [Computational Turing Test Reveals Systematic Differences Between Human and AI Language](https://mlsanity.com/paper/2511.04195/) (2025)
- [Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data](https://mlsanity.com/paper/2509.18985/) (2025)
- [Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation](https://mlsanity.com/paper/2508.03385/) (2025)
- [The Collective Turing Test: Large Language Models Can Generate Realistic Multi-User Discussions](https://mlsanity.com/paper/2511.08592/) (2025)

## Abstract (arXiv)

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.