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 2608.13659cs.CR

“我以为你是未经审查的地方”:AI生成性内容社区的规范、规则与审核

"I Thought You Were The Uncensored Place": Norms, Rules, and Moderation in AI-Generated Sexual Content Communities

  • Georgetown University(乔治城大学)
  • Arizona State University(亚利桑那州立大学)

机构由 AI 辅助整理,请以论文原文为准。

Lucy Qin, Jaron Mink, Elissa M. Redmiles

AI总结:

本研究通过访谈24名大型AI生成性内容社区的成员及审核员,揭示了这类社区的形成机制、规范规则及治理困境,并反思了缓解滥用内容生产的多维度治理路径。

AI中文摘要:

随着AI生成性内容(AIG-SC)的生产日益增多,在线社区应运而生以满足创作者的需求。为了解社区治理尝试是否以及如何在支持自由表达的同时防止滥用,我们对大型AIG-SC在线社区(成员超1万人)的24名成员及审核员进行了访谈,这些社区明确制定了禁止创建和分享滥用内容(如AI生成的儿童性虐待材料)的规则。通过深度访谈,我们提供了四方面的见解:(1)这些社区的形成方式及原因;(2)隐性社区规范;(3)明确表述的规则及其通过内容审核的实施;(4)社区价值观与审核之间的紧张关系,这种紧张关系为滥用行为留下了空间。我们的研究结果揭示了一幅复杂图景:尽管许多创作者和社区对滥用行为有个人界限,但无论用户意图如何,都能获取任何形式AI生成性内容的创作建议和资源。进一步使社区审核复杂化的是反审查和非评判的规范,这使得审核员需借助法律限制和服务条款来为自身行为辩护。最后,我们反思了技术、社区和法律治理可最有效缓解滥用内容生产的方式。

英文摘要:

As AI-generated sexual content (AIG-SC) is increasingly produced, online communities have emerged to support creators' needs. To understand whether and how community governance attempts work to prevent abuse while supporting free expression, we interviewed 24 members and moderators of large AIG-SC online communities (10,000+ members) with stated rules against creating and sharing abusive content (e.g., AI-generated CSAM). Through in-depth interviews, we offer insight into: (1) how and why these communities form; (2) implicit community norms; (3) explicitly stated rules---and their operationalization via content moderation; and (4) tensions between community values and moderation that leave space for abusive behavior. Our findings reveal a complex picture: while many creators and communities have personal boundaries against abuse, advice and resources for creating any form of AI-generated sexual content are accessible to users regardless of their intentions. Further complicating community moderation are norms that center anti-censorship and non-judgment, which leave moderators to justify their actions using the limits of the law and terms of service. We end by reflecting on the ways in which technical, community, and legal governance may most effectively mitigate the production of abusive content.

补充信息

↑