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 2312.02401stat.MLcs.LGcs.SI
收藏

增强内容审核的文化感知模型

Enhancing Content Moderation with Culturally-Aware Models

Spotify;University of Cambridge(剑桥大学);Sapienza University, Rome(罗马大学)

Alex J. Chan, José Luis Redondo García, Fabrizio Silvestri, Colm O'Donnell, Konstantina Palla

AI总结:

本研究提出一个文化感知框架,通过微调模型并整合到内容审核流程,提升本地违规检测准确性,促进公平文化敏感的内容审核。

摘要:

全球范围内的内容审核必须应对一系列复杂的本地文化差异,这可能会阻碍有效的执行。虽然全球政策旨在追求一致性和广泛适用性,但往往忽略了区域语言解释、文化信仰和地方法规的细微差别。本工作引入了一个灵活的框架,通过文化知识增强基础语言模型。我们的方法涉及在媒体消费数据上微调解码器-编码器模型以捕捉文化细微差别,并应用持续训练机制将这些模型有效整合到内容审核流程中。我们在一个涵盖多个地区内容的在线播客平台的案例研究中评估了该框架。结果表明,我们的文化适应模型提高了本地违规检测的准确性,并提供了更符合区域文化规范的解释。我们的研究结果强调了需要一种适应性强的内容审核方法,该方法在面对其运作所涉及的多样化文化景观时保持灵活性,并代表了朝着更公平和文化敏感的内容审核框架迈出的一步,展示了在该领域可实现的目标。

英文摘要:

Content moderation on a global scale must navigate a complex array of local cultural distinctions, which can hinder effective enforcement. While global policies aim for consistency and broad applicability, they often miss the subtleties of regional language interpretation, cultural beliefs, and local legislation. This work introduces a flexible framework that enhances foundation language models with cultural knowledge. Our approach involves fine-tuning encoder-decoder models on media-diet data to capture cultural nuances, and applies a continued training regime to effectively integrate these models into a content moderation pipeline. We evaluate this framework in a case study of an online podcast platform with content spanning various regions. The results show that our culturally adapted models improve the accuracy of local violation detection and offer explanations that align more closely with regional cultural norms. Our findings reinforce the need for an adaptable content moderation approach that remains flexible in response to the diverse cultural landscapes it operates in and represents a step towards a more equitable and culturally sensitive framework for content moderation, demonstrating what is achievable in this domain.

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。

↑