arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.03068cs.CYcs.AI
收藏

AI危害的回响:一种人机协同框架用于偏见驱动的危害预见

ECHO: A Participatory Framework for Bias-Anchored AI Harm Anticipation

Aristotle University(亚里士多德大学)

Nicoleta Tantalaki, Sophia Vei, Athena Vakali

AI总结:

本文提出ECHO框架,通过系统映射人工智能偏见类型到危害结果,实现主动危害预见,用于高风险领域中的偏见驱动危害检测与治理。

摘要:

随着人工智能系统在关键领域决策中的影响力增长,其造成重大危害的潜力已被暴露,这些危害往往根植于人工智能生命周期中的偏见。尽管现有框架和分类学记录偏见或危害,但很少能建立特定偏见类型与所造成危害之间的系统联系,特别是在现实社会技术环境中。为了解决人工智能偏见而提出的技术解决方案往往无法有效应对,且通常在系统开发或部署后才被应用,提供有限的预防价值。我们提出了ECHO,一种通过系统地将人工智能偏见类型映射到不同利益相关者和领域背景下的危害结果,从而实现主动人工智能危害预见的新型框架。ECHO遵循一个模块化的工作流程,包括利益相关者识别、基于场景的偏见人工智能系统的呈现,以及双(人类-LLM)危害注释,整合在伦理矩阵中以实现结构化解释。这种以人类为中心的方法能够早期发现偏见到危害的路径,指导人工智能设计和治理决策。我们在两个高风险领域(疾病诊断和招聘)中验证了ECHO,揭示了领域特定的偏见到危害模式,并展示了ECHO在支持人工智能系统前瞻性治理方面的潜力。

英文摘要:

Artificial Intelligence (AI) systems increasingly shape consequential decisions, creating value but also potential harms for individuals, social groups, and society. This has prompted calls for proactive approaches that anticipate harms early in the AI lifecycle. Although prior research identifies AI biases as sources of harm, the associations between particular lifecycle biases and harms remain insufficiently understood. We introduce \texttt{ECHO}, a systematic, context-sensitive, and participatory framework that anchors early harm anticipation in lifecycle biases and elicits their perceived associations with potential harms.\texttt{ECHO} identifies domain-specific stakeholders, instantiates biases through vignettes, collects harm judgements from human participants and a large language model (LLM), and organises them into descriptive and inferential ethical matrices. Applied to disease diagnosis and hiring, \texttt{ECHO} surfaced non-uniform, context-sensitive bias--harm patterns indicating which harms were perceived as plausible consequences of particular AI biases. The theoretical interpretability of these patterns and the inferential support for specific associations strengthen the plausibility of the mappings. By linking stakeholder-specific anticipated harms to lifecycle biases, \texttt{ECHO} supports source-level harm anticipation and provides structured input to subsequent AI governance actions

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。

↑