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 2501.19173cs.CY
收藏

立场论文:情境完整性在语言模型中的应用尚不充分

Position: Contextual Integrity is Inadequately Applied to Language Models

Yan Shvartzshnaider, Vasisht Duddu

AI总结:

本文指出当前研究将情境完整性用于LLM隐私评估时未贯彻其基本原则,并梳理四项原则、既有偏差及实验规范问题。

摘要:

机器学习领域正在发现情境完整性(Contextual Integrity,CI)是评估大型语言模型(LLM)隐私影响的有用框架。这是一个令人鼓舞的进展。CI理论强调按照隐私规范共享信息,并能够架起评估LLM隐私所必需的社会、法律、政治和技术层面之间的桥梁。然而,现在也是反思CI在LLM中使用情况的好时机。本立场论文认为,现有文献在将CI应用于LLM时并不充分,没有采纳该理论的基本原则。不充分的CI应用可能导致错误结论和有缺陷的隐私保护设计。我们阐明了CI理论的四项基本原则,系统梳理了以往研究在这些原则上是否存在偏离,并强调了LLM实验规范中被忽视的问题(例如提示敏感性、位置偏差)。

英文摘要:

Machine learning community is discovering Contextual Integrity (CI) as a useful framework to assess the privacy implications of large language models (LLMs). This is an encouraging development. The CI theory emphasizes sharing information in accordance with privacy norms and can bridge the social, legal, political, and technical aspects essential for evaluating privacy in LLMs. However, this is also a good point to reflect on use of CI for LLMs. This position paper argues that existing literature inadequately applies CI for LLMs without embracing the theory's fundamental tenets. Inadequate applications of CI could lead to incorrect conclusions and flawed privacy-preserving designs. We clarify the four fundamental tenets of CI theory, systematize prior work on whether they deviate from these tenets, and highlight overlooked issues in experimental hygiene for LLMs (e.g., prompt sensitivity, positional bias).

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。

↑