[论文解读] Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies

Emilio Ferrara|arXiv (Cornell University)|Apr 16, 2023

Ethics and Social Impacts of AI参考文献 51被引用 74

一句话总结

本论文综述了 AI 的公平性、偏见的来源、社会影响及缓解策略，强调生成式 AI 偏见及需要跨学科方法。

ABSTRACT

The significant advancements in applying Artificial Intelligence (AI) to healthcare decision-making, medical diagnosis, and other domains have simultaneously raised concerns about the fairness and bias of AI systems. This is particularly critical in areas like healthcare, employment, criminal justice, credit scoring, and increasingly, in generative AI models (GenAI) that produce synthetic media. Such systems can lead to unfair outcomes and perpetuate existing inequalities, including generative biases that affect the representation of individuals in synthetic data. This survey paper offers a succinct, comprehensive overview of fairness and bias in AI, addressing their sources, impacts, and mitigation strategies. We review sources of bias, such as data, algorithm, and human decision biases - highlighting the emergent issue of generative AI bias where models may reproduce and amplify societal stereotypes. We assess the societal impact of biased AI systems, focusing on the perpetuation of inequalities and the reinforcement of harmful stereotypes, especially as generative AI becomes more prevalent in creating content that influences public perception. We explore various proposed mitigation strategies, discussing the ethical considerations of their implementation and emphasizing the need for interdisciplinary collaboration to ensure effectiveness. Through a systematic literature review spanning multiple academic disciplines, we present definitions of AI bias and its different types, including a detailed look at generative AI bias. We discuss the negative impacts of AI bias on individuals and society and provide an overview of current approaches to mitigate AI bias, including data pre-processing, model selection, and post-processing. We emphasize the unique challenges presented by generative AI models and the importance of strategies specifically tailored to address these.

研究动机与目标

• 在 AI 应用（医疗、就业、刑事司法、信用、GenAI）中推动对公平问题的研究。
• 刻画偏见来源（数据、算法、人为决策）并定义 AI 偏见与生成式 AI 偏见。
• 探讨偏见 AI 的社会影响和刻板印象的强化。
• 评审缓解策略（数据预处理、模型选择、后处理）及伦理考量。

提出的方法

• 在多个学科领域进行系统文献综述。
• 提供 AI 偏见的定义与类型学，包括生成式 AI 偏见。
• 讨论缓解策略及其伦理含义。
• 强调挑战以及为提高有效性所需的跨学科协作。

实验结果

研究问题

• RQ1 AI 系统中的主要偏见来源是什么（数据、算法、人为决策）？
• RQ2 偏见 AI 尤其是生成式 AI 的社会影响是什么？
• RQ3 存在哪些 AI 偏见的缓解策略，以及它们包含哪些伦理考量？
• RQ4 应如何组织跨学科协作以解决 AI 的公平性和偏见？

主要发现

• 偏见 AI 源自数据、算法和人类决策过程。
• 生成式 AI 偏见是一个新兴问题，可能再现并放大社会刻板印象。
• 偏见 AI 可能在各领域延续不平等并强化有害的刻板印象。
• 缓解方法包括数据预处理、模型选择和后处理，每种方法都具有伦理考量。
• 生成式 AI 提出独特挑战，需要量身定制的策略。