Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes

Mahammed Kamruzzaman, Gene Louis Kim


Abstract
Dual process theory posits that human cognition arises via two systems. System 1, which is a quick, emotional, and intuitive process, which is subject to cognitive biases, and System 2, is a slow, onerous, and deliberate process. Prior research in LLMs found that using chain-ofthought (CoT) prompting in LLMs, which has been often compared to System 2 reasoning, can lead to reduced gender bias. Along these lines, we investigate the relationship between bias, CoT prompting, a direct debiasing, and dual process theory modeling in LLMs. We compare zero-shot CoT, debiasing, and dual process theory-based prompting strategies on two bias datasets spanning nine different social bias categories. We incorporate human and machine personas to determine whether LLM modeling of the effects of dual process theory exist independent of explicit persona models or are tied to the LLM’s modeling of human-like generation. We find that a human persona, debiasing, System 2, and CoT prompting all tend to reduce social biases in LLMs, though the best combination of features depends on the exact model and bias category—resulting in up to a 33 percent drop in stereotypical judgments by an LLM.
Anthology ID:
2025.ranlp-1.60
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
511–520
Language:
URL:
https://aclanthology.org/2025.ranlp-1.60/
DOI:
Bibkey:
Cite (ACL):
Mahammed Kamruzzaman and Gene Louis Kim. 2025. Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 511–520, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes (Kamruzzaman & Kim, RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.60.pdf