说点别的：重新思考上下文隐私作为信息充分性
Say Something Else: Rethinking Contextual Privacy as Information Sufficiency
AI总结：
本文提出信息充分性任务，引入自由文本假名化策略，并设计对话评估协议，评估七种前沿LLM在隐私、隐蔽性和效用上的表现。
摘要：
随着LLM代理越来越多地代表用户起草信息，用户经常过度分享敏感信息且对隐私定义存在分歧。现有系统仅支持抑制和泛化，且通常仅在单条信息上评估，导致策略空间和评估设置不完整。本文将隐私保护的LLM通信形式化为信息充分性任务，引入自由文本假名化作为第三种策略，并提出对话评估协议，评估策略在现实多轮对话压力下的表现。在792个场景中，涵盖三种权力关系类型（机构、同伴、亲密）和三种敏感类别（歧视风险、社会成本、边界），评估七种前沿LLM在隐私、隐蔽性和效用上的表现。假名化在整体隐私-效用权衡中表现最佳，单信息评估系统性低估了信息泄露，泛化在多轮对话下可能损失高达16.3个百分点的隐私。
英文摘要：
LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only suppression (omitting sensitive information) and generalization (replacing information with an abstraction), and are typically evaluated on single isolated messages, leaving both the strategy space and evaluation setting incomplete. We formalize privacy-preserving LLM communication as an \textbf{Information Sufficiency (IS)} task, introduce \textbf{free-text pseudonymization} as a third strategy that replaces sensitive attributes with functionally equivalent alternatives, and propose a \textbf{conversational evaluation protocol} that assesses strategies under realistic multi-turn follow-up pressure. Across 792 scenarios spanning three power-relation types (institutional, peer, intimate) and three sensitivity categories (discrimination risk, social cost, boundary), we evaluate seven frontier LLMs on privacy at two granularities, covertness, and utility. Pseudonymization yields the strongest privacy\textendash utility tradeoff overall, and single-message evaluation systematically underestimates leakage, with generalization losing up to 16.3 percentage points of privacy under follow-up.
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。
