arXiv cs.AI· Omer Ebead, Claude Formanek, Joel Z. Leibo·· 11 小时前AI 评分31
用生成模型研究上下文完整性：LLM 对话中的信息分享与拒绝
A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing
AI 导读
研究者构建了一个上下文完整性的生成模型，让两个由大语言模型扮演的角色在模拟对话中交换信息，一方持有隐私信息、另一方索取。结果显示，角色会在信息确有需要时分享给合法接收者，但也会向无权获取的人泄露信息。该模型可用于研究披露与拒绝行为如何随情境、持有者的决策逻辑、性格倾向及底层语言模型而变化，论文已被 NeurIPS 2026 接收为主会论文。
正文 · 原文
Abstract:Contextual integrity (CI) holds that appropriate information flow depends on context-specific norms. The same disclosure may be appropriate in one context and inappropriate in another. We build a generative model of contextual integrity to study information sharing through simulated conversations. Two actors played by large language models exchange messages, with one holding private information and the other seeking it. We examine how sharing and refusal vary with the situation, the holder's decision logic, disposition, and the underlying language model. Actors shared information with the rightful recipients when it was needed, but also disclosed it to people who were not entitled to receive it. The model provides a way to study how disclosure and refusal develop through conversation as the situations and the actors vary.
| Comments: | Accepted as a main conference paper at NeurIPS 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.08284 [cs.AI] |
| (or arXiv:2611.08284v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08284 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joel Leibo [view email]
[v1]
Thu, 5 Nov 2026 16:48:31 UTC (89 KB)
来源：arXiv cs.AI · arxiv.org