通过系统1与系统2认知过程减少大语言模型中社会偏见的提示技术
Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes
AI总结：
本文研究如何通过系统1/系统2双过程理论、思维链提示和去偏策略减少大语言模型的社会偏见，发现这些方法普遍有效，最佳组合因模型和偏见类别而异，可使刻板判断最多降低33%。
摘要：
双过程理论认为，人类认知通过两个系统产生。系统1是一个快速、情绪化和直觉性的过程，容易受到认知偏见的影响；系统2则是一个缓慢、费力且深思熟虑的过程。此前针对大语言模型（LLMs）的研究发现，在LLMs中使用思维链（chain-of-thought，CoT）提示——通常被类比为系统2推理——可以降低性别偏见。沿着这一思路，我们研究了LLMs中偏见、CoT提示、直接去偏以及双过程理论建模之间的关系。我们在两个偏见数据集上比较了零样本CoT、去偏以及基于双过程理论的提示策略，这些数据集涵盖九种不同的社会偏见类别。我们引入人类角色和机器角色，以确定LLMs对双过程理论效应的建模是否独立于显式角色模型存在，还是与LLMs对人类式生成的建模相关联。我们发现，人类角色、去偏、系统2和CoT提示都倾向于减少LLMs中的社会偏见，尽管最佳特征组合取决于具体模型和偏见类别——最终使LLM的刻板判断最多下降33%。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
