让智能助手协作补全对话上下文，保护隐私不泄露。
Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI
- 助手间异步协作，仅记录主人语音，避免捕获他人说话。
- 91.4%漏检率检测、96%关系识别准确率、97%隐私决策真负率。
- 适合需隐私保护的主动监听场景，如家庭智能助手。
我们提出 CONCORD，一种面向隐私保护的异步助手间（A2A）协作框架，利用主动语音智能体间的协作应对始终监听带来的隐私风险。随着智能体从被动响应向持续监听演进，其捕获非同意说话者语音的风险成为社会部署的障碍。CONCORD 通过实时说话人验证，仅允许主人语音被记录，生成单边转录，虽导致上下文缺失，但保障隐私。我们证明，CONCORD 可通过（1）时空上下文恢复，（2）信息缺口检测，（3）基于关系感知披露的最小化助手查询，安全恢复必要上下文。不同于易幻觉的推断，CONCORD 将上下文恢复视为助手间的协商式安全交换。在多领域对话数据集上，CONCORD 实现 91.4% 的缺口检测召回率、96% 的关系分类准确率，以及 97% 的隐私敏感披露决策真负率。通过将始终监听智能体重构为隐私保护代理间的协调问题，CONCORD 为可社会部署的主动对话代理提供可行路径。
原文摘要 · Abstract (English)
We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core privacy risk (of capturing non-consenting speakers), which makes their social deployment a challenge. To overcome this, we implement CONCORD, which enforces owner-only speech capture via real-time speaker verification, producing a one-sided transcript that incurs missing context but preserves privacy. We demonstrate that CONCORD can safely recover necessary context through (1) spatio-temporal context resolution, (2) information gap detection, and (3) minimal A2A queries governed by a relationship-aware disclosure. Instead of hallucination-prone inferring, CONCORD treats context recovery as a negotiated safe exchange between assistants. Across a multi-domain dialogue dataset, CONCORD achieves 91.4% recall in gap detection, 96% relationship classification accuracy, and 97% true negative rate in privacy-sensitive disclosure decisions. By reframing always-listening AI as a coordination problem between privacy-preserving agents, CONCORD offers a practical path toward socially deployable proactive conversational agents.
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。