arXiv:2412.13678cs.CYcs.AI2024-12被引 99

用AI分析百万对话,不看原始内容也能看清真实使用场景。

Clio: Privacy-Preserving Insights into Real-World AI Use

  • 让AI助手自我分析对话数据,实现无隐私泄露的规模化使用洞察。
  • 从百万级对话中提炼出编码、写作、研究等核心用途及语言差异模式。
  • 适合关注AI安全、治理与真实应用落地的研究者和开发者。

AI助手在现实中的使用情况如何?尽管模型提供商理论上可通过用户数据了解影响,但隐私顾虑与实际挑战使得数据分析困难。为此,我们提出Clio(Claude insights and observations),一个隐私保护平台,利用AI助手自身分析数百万对话的聚合模式,无需人工阅读原始内容。通过大量评估验证了该方法在高准确率与强隐私保护下的可行性。我们展示了两方面应用:一、基于一百万条Claude.ai免费与专业版对话,揭示了从发型建议到Git操作指导等多样用途,并识别出编码、写作、研究为三大主要使用场景;同时发现日语对话中关于养老与老龄化讨论频率显著高于其他语言。二、借助Clio提升系统安全性,识别协同滥用行为,监测新功能发布或重大事件期间的未知风险,优化现有监控机制。我们还讨论了方法局限性及伦理风险。Clio为实证驱动的AI安全与治理提供了可扩展的分析平台。

原文摘要 · Abstract (English)

How are AI assistants being used in the real world? While model providers in theory have a window into this impact via their users' data, both privacy concerns and practical challenges have made analyzing this data difficult. To address these issues, we present Clio (Claude insights and observations), a privacy-preserving platform that uses AI assistants themselves to analyze and surface aggregated usage patterns across millions of conversations, without the need for human reviewers to read raw conversations. We validate this can be done with a high degree of accuracy and privacy by conducting extensive evaluations. We demonstrate Clio's usefulness in two broad ways. First, we share insights about how models are being used in the real world from one million Claude.ai Free and Pro conversations, ranging from providing advice on hairstyles to providing guidance on Git operations and concepts. We also identify the most common high-level use cases on Claude.ai (coding, writing, and research tasks) as well as patterns that differ across languages (e.g., conversations in Japanese discuss elder care and aging populations at higher-than-typical rates). Second, we use Clio to make our systems safer by identifying coordinated attempts to abuse our systems, monitoring for unknown unknowns during critical periods like launches of new capabilities or major world events, and improving our existing monitoring systems. We also discuss the limitations of our approach, as well as risks and ethical concerns. By enabling analysis of real-world AI usage, Clio provides a scalable platform for empirically grounded AI safety and governance.

AI治理隐私保护使用分析

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。