浏览器中的搜索助手代理
In-Browser Agents for Search Assistance
AI总结:
本文提出了一种浏览器内隐私保护的搜索助手代理,结合自适应概率模型与小语言模型,提升搜索效率同时保障用户隐私。
摘要:
在网页搜索中对复杂AI辅助的需求与用户数据隐私的需要之间存在根本性矛盾。当前集中式模型要求用户将敏感浏览数据传输到外部服务,这限制了用户的控制权。本文提出了一种浏览器扩展程序,提供了一种可行的浏览器内替代方案。我们介绍了一种混合架构,该架构完全在客户端侧运行,结合了两个组件:(1)一个自适应概率模型,从直接反馈中学习用户的策略;(2)一个在浏览器中运行的小语言模型(SLM),由概率模型支撑,以生成上下文感知的建议。为了评估这种方法,我们进行了为期三周的纵向用户研究,参与了18名参与者。我们的结果表明,这种隐私保护的方法在适应个体用户行为方面非常有效,导致搜索效率显著提高。这项工作证明了在不牺牲用户隐私或数据控制的情况下,复杂AI辅助是可行的。
英文摘要:
A fundamental tension exists between the demand for sophisticated AI assistance in web search and the need for user data privacy. Current centralized models require users to transmit sensitive browsing data to external services, which limits user control. In this paper, we present a browser extension that provides a viable in-browser alternative. We introduce a hybrid architecture that functions entirely on the client side, combining two components: (1) an adaptive probabilistic model that learns a user's behavioral policy from direct feedback, and (2) a Small Language Model (SLM), running in the browser, which is grounded by the probabilistic model to generate context-aware suggestions. To evaluate this approach, we conducted a three-week longitudinal user study with 18 participants. Our results show that this privacy-preserving approach is highly effective at adapting to individual user behavior, leading to measurably improved search efficiency. This work demonstrates that sophisticated AI assistance is achievable without compromising user privacy or data control.
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。