Large Language Model-driven Multi-Agent Simulation for News Diffusion Under Different Network Structures

TL;DR

<3-5 sentence high-level summary> Addresses fake news diffusion on social platforms and the limitations of traditional models. Proposes an LLM-driven multi-agent simulation that captures micro- and macro-level diffusion across diverse network topologies. Finds that agent personality traits (notably Extraversion and Openness) and network structure (scale-free fastest diffusion; high-brokerage slowest) significantly influence spread, with countermeasures showing topology-dependent effectiveness. Demonstrates the potential of LLM-based simulations to reveal diffusion mechanisms and inform topology-aware misinformation mitigation strategies.

Abstract

The proliferation of fake news in the digital age has raised critical concerns, particularly regarding its impact on societal trust and democratic processes. Diverging from conventional agent-based simulation approaches, this work introduces an innovative approach by employing a large language model (LLM)-driven multi-agent simulation to replicate complex interactions within information ecosystems. We investigate key factors that facilitate news propagation, such as agent personalities and network structures, while also evaluating strategies to combat misinformation. Through simulations across varying network structures, we demonstrate the potential of LLM-based agents in modeling the dynamics of misinformation spread, validating the influence of agent traits on the diffusion process. Our findings emphasize the advantages of LLM-based simulations over traditional techniques, as they uncover underlying causes of information spread -- such as agents promoting discussions -- beyond the predefined rules typically employed in existing agent-based models. Additionally, we evaluate three countermeasure strategies, discovering that brute-force blocking influential agents in the network or announcing news accuracy can effectively mitigate misinformation. However, their effectiveness is influenced by the network structure, highlighting the importance of considering network structure in the development of future misinformation countermeasures.

Figures (8)

• Figure 1: The prompt designed for LLM agents to make decisions on news diffusion without any intervention strategy.
• Figure 2:
• Figure 3: The proportion of agents who have received the news under different network structures.
• Figure 4: A micro-level observation reveals the details of an agent's thought process.
• Figure 5: An example showing the comment left by an agent when sharing the news.