arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.07683cs.CY
收藏

人工智能中的公平性与偏见:来源、影响及缓解策略简要综述

Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies

Emilio Ferrara

AI总结:

本文综述AI偏见的数据、算法与人为来源、社会影响及预处理、模型选择和后处理等缓解方法,并重点分析生成式AI偏见的独特挑战。

摘要:

人工智能(AI)在医疗决策、医学诊断及其他领域应用中的重大进展,同时也引发了人们对AI系统公平性与偏见的担忧。这在医疗、就业、刑事司法、信用评分等领域尤为关键,并且在生成合成媒体的生成式AI模型(GenAI)中也日益突出。此类系统可能导致不公平结果并使既有不平等长期存在,包括影响个人在合成数据中表征的生成性偏见。本综述论文对AI中的公平性与偏见进行了简明而全面的概述,阐述其来源、影响和缓解策略。我们回顾了偏见的来源,例如数据、算法和人类决策偏见,并重点指出新兴的生成式AI偏见问题,即模型可能复现并放大社会刻板印象。我们评估了有偏见的AI系统对社会的影响,聚焦于不平等的延续以及有害刻板印象的强化,尤其是在生成式AI越来越多地被用于创作影响公众认知的内容之际。我们探讨了已提出的多种缓解策略,讨论其实施中的伦理考量,并强调需要跨学科协作以确保有效性。通过跨越多个学术学科的系统性文献综述,我们给出了AI偏见及其不同类型的定义,包括对生成式AI偏见的详细考察。我们讨论了AI偏见对个人和社会的负面影响,并概述了当前缓解AI偏见的方法,包括数据预处理、模型选择和后处理。我们强调了生成式AI模型所带来的独特挑战,以及专门针对这些挑战制定策略的重要性。

英文摘要:

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.

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。

↑