# Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in Healthcare

arXiv: https://arxiv.org/abs/2504.08260 · HTML: https://mlsanity.com/paper/2504.08260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 9 of 9)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation](https://mlsanity.com/paper/2407.01093/) (2024)
- [Bias patterns in the application of LLMs for clinical decision support: A comprehensive study](https://mlsanity.com/paper/2404.15149/) (2024)
- [The Butterfly Effect in Artificial Intelligence Systems: Implications for AI Bias and Fairness](https://mlsanity.com/paper/2307.05842/) (2023)

## Abstract (arXiv)

Generative agents have been increasingly used to simulate human behaviour in silico, driven by large language models (LLMs). These simulacra serve as sandboxes for studying human behaviour without compromising privacy or safety. However, it remains unclear whether such agents can truly represent real individuals. This work compares survey data from the Understanding America Study (UAS) on healthcare decision-making with simulated responses from generative agents. Using demographic-based prompt engineering, we create digital twins of survey respondents and analyse how well different LLMs reproduce real-world behaviours. Our findings show that some LLMs fail to reflect realistic decision-making, such as predicting universal vaccine acceptance. However, Llama 3 captures variations across race and Income more accurately but also introduces biases not present in the UAS data. This study highlights the potential of generative agents for behavioural research while underscoring the risks of bias from both LLMs and prompting strategies.