Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations
cs.AI, cs.SI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/azza-bouleimen/ITE-LLMs-in-social-media
Sources
- The Collective Turing Test: Large Language Models Can Generate Realistic Multi-User Discussions
- Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data
- Emergence of Scale-Free Networks in Social Interactions among Large Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- The Llama 3 Herd of Models
- S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents
- Accumulating Context Changes the Beliefs of Language Models
- SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
- Mistral 7B
- Gemma 3 Technical Report
- Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation
- Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations
- Computational Turing Test Reveals Systematic Differences Between Human and AI Language
- Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
- Qwen2.5 Technical Report
- OASIS: Open Agent Social Interaction Simulations with One Million Agents
- The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems