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

TL;DR

This paper explores how different prompting strategies, inspired by dual process theory, can reduce social biases in large language models, showing that combining human personas, debiasing, and Chain-of-Thought prompting can significantly decrease stereotypical judgments.

Contribution

It introduces dual process theory-based prompting strategies and compares their effectiveness with existing methods in reducing social bias in LLMs.

Findings

System 2 and CoT prompting reduce social biases.

Human personas and debiasing further decrease stereotypes.

Up to 33% reduction in stereotypical judgments achieved.

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-of-thought (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.