# Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations

arXiv: https://arxiv.org/abs/2410.15442 · HTML: https://mlsanity.com/paper/2410.15442/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 20 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction](https://mlsanity.com/paper/2305.09620/) (2023)
- [A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models](https://mlsanity.com/paper/2403.12025/) (2024)

## Built on by (most cited first, 5 of 5)

- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates](https://mlsanity.com/paper/2608.29455/) (2026)
- [Automated Item Neutralization for Non-Cognitive Scales: A Large Language Model Approach to Reducing Social-Desirability Bias](https://mlsanity.com/paper/2509.19314/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are employed to simulate human-like responses in social surveys, yet it remains unclear if they develop biases like social desirability response (SDR) bias. To investigate this, GPT-4 was assigned personas from four societies, using data from the 2022 Gallup World Poll. These synthetic samples were then prompted with or without a commitment statement intended to induce SDR. The results were mixed. While the commitment statement increased SDR index scores, suggesting SDR bias, it reduced civic engagement scores, indicating an opposite trend. Additional findings revealed demographic associations with SDR scores and showed that the commitment statement had limited impact on GPT-4's predictive performance. The study underscores potential avenues for using LLMs to investigate biases in both humans and LLMs themselves.