Debiasing International Attitudes: LLM Agents for Simulating US-China Perception Changes

TL;DR

This paper develops an LLM-agent framework to simulate and analyze US attitudes toward China, introducing debiasing mechanisms to produce more human-like opinions and exploring media influence and inherent model biases.

Contribution

It presents a novel LLM-agent-based approach for modeling opinion evolution and introduces three debiasing techniques to improve the realism of simulated attitudes.

Findings

Devise an LLM-agent framework for opinion simulation from 2005 to 2025.

Identify that the devil's advocate mechanism most effectively mitigates negative attitude trends.

Discover region-specific biases linked to models' geographic origins.

Abstract

Large Language Models (LLMs) offer transformative opportunities to address the longstanding challenge of modeling opinion evolution in computational social science. This study investigates how media influences cross-border attitudes - a key driver of global polarization - by developing an LLM-agent framework to disentangle sources of bias and assess LLMs' capacity for human-like opinion formation in response to external information. We introduce an LLM-agent-based framework that models U.S. citizens' attitudes toward China from 2005 to 2025. Our approach integrates large-scale news data with social media profiles to initialize agent populations, which then undergo cognitive-aware reflection and opinion updating. We propose three debiasing mechanisms: (1) fact elicitation, extracting neutral events from subjectively framed news; (2) a devil's advocate agent that simulates critical contextualization; and (3) counterfactual exposure to surface inherent model biases. Simulations with two state-of-the-art LLMs (Qwen3-14b and GPT4o) reveal the expected negative attitudinal trend following media exposure. While all three mechanisms mitigate this trend to varying degrees, results indicate that subjective news framing contributes only modestly to negative attitudes, whereas the devil's advocate agent proves most effective overall, suggesting that intermediate analytical steps can produce more human-like agent opinions. Notably, the counterfactual study reveals contradictory findings across models, suggesting region-specific inherent biases tied to models' geographic origins. By advancing understanding of LLM-based opinion formation and debiasing methods, this study contributes to developing more objective models that better align with human cognitive tendencies.