Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
By Apostolos Filippas, John Joseph Horton, Benjamin S. Manning. 2023
495 citations recorded by the source corpus.
Large language models---because of how they are trained and designed---are implicit computational models of humans---a homo silicus. Social scientists can use LLMs like economists use homo economicus: LLMs can be given endowments, information, preferences, and so on, and then their behavior can be explored in scenarios via simulation. We replicate four experiments using this approach and find qualitatively similar results to the original. Benefits of this approach include trying new variations for fresh insights, piloting studies via simulation, and searching for novel social science insights to test in the real world. The full version of the paper can be accessed at https://apostolos-filippas.com/papers/hs.pdf.
Subfields: Sociology and Political Science
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ji-rong Wen
- Wayne Xin Zhao
- Zeyu Zhang
- Lei Wang
- Chengbang Ma
- Yankai Lin
- Xueyang Feng
- Hao-ran Yang
Citations in the corpus
- Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, unknown): “[ Chen et al. , 2023b ] proposes an LLM-based consensus-seeking framework, which can be applied as a co-operative planner to a multi-robot aggregation task.”
- S3: Social-network Simulation System with Large Language Model-Empowered Agents (2023, unknown): “Consequently, researchers [1, 17, 15, 28] leverage LLMs as agent-like entities for simulating human-like behavior, capitalizing on three fundamental capabilities.”
- Large language models empowered agent-based modeling and simulation: a survey and perspectives (2023, unknown): “…goal of related research is to simulate the human-like economic decision-making capabilities of LLMs (Bauer et al., 2023; Chen et al., 2023e; Geerling et al., 2023; Horton, 2023) or their understanding of economic phenomena (Bybee, 2023; Faria-e Castro and Leibovici, 2023; Xie et al., 2023).”
- A survey on large language model based autonomous agents (2023, background): “Civil Engineering : In civil engineering, LLM-based agents can be used to design and optimize Out of One [29], Horton [106], Ziems et al. [105] Social Simulation Social Simulacra [79], Generative Agents [20], SocialAI School [109], AgentSims [34], S 3 [77], Williams et al. [110], Li et al. [107], Ch”