# Automated Item Neutralization for Non-Cognitive Scales: A Large Language Model Approach to Reducing Social-Desirability Bias

arXiv: https://arxiv.org/abs/2509.19314 · HTML: https://mlsanity.com/paper/2509.19314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 56 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer](https://mlsanity.com/paper/2502.15631/) (2025)
- [Fine-tuning and Utilization Methods of Domain-specific LLMs](https://mlsanity.com/paper/2401.02981/) (2024)
- [Large Language Models Show Human-like Social Desirability Biases in Survey Responses](https://mlsanity.com/paper/2405.06058/) (2024)
- [Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chains](https://mlsanity.com/paper/2306.12028/) (2023)
- [GPT for Games: An Updated Scoping Review (2020-2024)](https://mlsanity.com/paper/2411.00308/) (2024)
- [Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations](https://mlsanity.com/paper/2410.15442/) (2024)

## Abstract (arXiv)

This study evaluates item neutralization assisted by the large language model (LLM) to reduce social desirability bias in personality assessment. GPT-o3 was used to rewrite the International Personality Item Pool Big Five Measure (IPIP-BFM-50), and 203 participants completed either the original or neutralized form along with the Marlowe-Crowne Social Desirability Scale. The results showed preserved reliability and a five-factor structure, with gains in Conscientiousness and declines in Agreeableness and Openness. The correlations with social desirability decreased for several items, but inconsistently. Configural invariance held, though metric and scalar invariance failed. Findings support AI neutralization as a potential but imperfect bias-reduction method.