提示公平性：集成因果性以消除大型语言模型的偏差
Prompting Fairness: Integrating Causality to Debias Large Language Models
AI总结：
本文提出一种因果性引导的去偏框架，通过识别社会信息影响LLM决策的因果路径并设计原则性提示策略进行调节，有效减少了模型决策中的社会偏见，并统一了现有提示去偏技术。
摘要：
大型语言模型（LLMs）尽管具有卓越的能力，却容易生成带有偏见和歧视性的回复。随着LLMs日益影响高风险决策（例如招聘和医疗保健），缓解这些偏见变得至关重要。在本研究中，我们提出了一个因果性引导的去偏框架来解决社会偏见，旨在减少LLMs决策与输入中的社会信息之间令人反感的依赖关系。我们的框架引入了一种新颖的视角，以识别社会信息如何通过不同的因果路径影响LLM的决策。利用这些因果见解，我们概述了通过选择机制调节这些路径的原则性提示策略。该框架不仅统一了现有的基于提示的去偏技术，而且通过鼓励模型优先考虑基于事实的推理而非依赖有偏见的社会线索，为减少偏见开辟了新方向。我们通过在多个领域的真实数据集上进行广泛实验验证了我们的框架，证明了其在消除LLM决策偏见方面的有效性，即使仅对模型进行黑盒访问也是如此。
英文摘要：
Large language models (LLMs), despite their remarkable capabilities, are susceptible to generating biased and discriminatory responses. As LLMs increasingly influence high-stakes decision-making (e.g., hiring and healthcare), mitigating these biases becomes critical. In this work, we propose a causality-guided debiasing framework to tackle social biases, aiming to reduce the objectionable dependence between LLMs' decisions and the social information in the input. Our framework introduces a novel perspective to identify how social information can affect an LLM's decision through different causal pathways. Leveraging these causal insights, we outline principled prompting strategies that regulate these pathways through selection mechanisms. This framework not only unifies existing prompting-based debiasing techniques, but also opens up new directions for reducing bias by encouraging the model to prioritize fact-based reasoning over reliance on biased social cues. We validate our framework through extensive experiments on real-world datasets across multiple domains, demonstrating its effectiveness in debiasing LLM decisions, even with only black-box access to the model.
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。
