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 2404.19256cs.AIcs.CYcs.GTcs.HCcs.LGcs.MA
收藏

AI、多元主义与(社会)补偿

AI, Pluralism, and (Social) Compensation

University of California, San Diego(加利福尼亚大学圣迭戈分校)

Nandhini Swaminathan, David Danks

AI总结:

本文探讨个性化AI系统在应对多元价值观时引发的社会补偿伦理问题,即AI为弥补人类队友缺陷可能采取欺骗性策略,并分析了此类补偿的正当性条件。

摘要:

应对用户群体中多元价值观的一种策略是实现AI系统的个性化:若AI能适应每个个体的特定价值观,我们便有可能规避多元主义带来的诸多挑战。然而,该方法引发了重大的伦理问题:若人机团队存在外部成功衡量标准,自适应AI系统可能会采取策略(有时具有欺骗性)来弥补人类队友的不足。这种现象可被视为一种社会补偿,即AI做决策并非基于预定目标,而是基于人类伙伴在团队绩效目标方面的缺陷。我们对此类补偿在何种条件下仍具正当性进行了实用的伦理分析。

英文摘要:

One strategy in response to pluralistic values in a user population is to personalize an AI system: if the AI can adapt to the specific values of each individual, then we can potentially avoid many of the challenges of pluralism. Unfortunately, this approach creates a significant ethical issue: if there is an external measure of success for the human-AI team, then the adaptive AI system may develop strategies (sometimes deceptive) to compensate for its human teammate. This phenomenon can be viewed as a form of social compensation, where the AI makes decisions based not on predefined goals but on its human partner's deficiencies in relation to the team's performance objectives. We provide a practical ethical analysis of the conditions in which such compensation may nonetheless be justifiable.

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。

↑