LLM agents simulate human macroeconomic expectations in survey experiments

Researchers have developed a new framework using Large Language Model (LLM) based agents to simulate macroeconomic expectations in survey experiments. These LLM agents are equipped with modules for personal characteristics, prior expectations, and external information. The framework successfully replicated three survey designs, generating expectation distributions similar to human data and capturing qualitative patterns in open-ended responses, offering insights into belief gaps between AI and humans. AI

IMPACT This research provides a novel method for understanding and potentially bridging the gap between AI and human economic expectations.

RANK_REASON The cluster contains an academic paper detailing a new framework for simulating macroeconomic expectations using LLM-based agents. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Lexuan Sun
• LLM Agents

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →