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 2502.13016cs.DBcs.AI
收藏

由 LLM 驱动的主动式数据系统

LLM-Powered Proactive Data Systems

UC Berkeley(加州大学伯克利分校)

Sepanta Zeighami, Yiming Lin, Shreya Shankar, Aditya Parameswaran

AI总结:

本文提出由 LLM 驱动的主动式数据系统,通过解析、重写、分解输入与数据及交互优化,克服反应式系统忽视操作、数据和用户意图的问题。

摘要:

借助 LLM 的能力,我们现在能够查询以往不可能查询的数据,包括文本、图像和视频。然而,尽管潜力巨大,当前大多数利用 LLM 的数据系统仍是反应式的,这反映出我们的研究群体希望将 LLM 映射到已知抽象。大多数数据系统把 LLM 视为不透明的黑盒,让其按原样处理用户输入和数据,并像对待任何其他近似且昂贵的 UDF 一样,结合其他关系运算符对其进行优化。这类数据系统只会照吩咐行事,却无法理解并利用 LLM 被要求执行的任务(即底层操作,而这些操作可能容易出错)、LLM 正在处理的数据(例如冗长复杂的文档),或用户真正的需求。它们没有利用当前操作和/或数据的特征,也没有在存在不精确性和歧义时确保结果的正确性。我们认为,数据系统反而需要具备主动性:它们需要被赋予更多能动性——在 LLM 能力的武装下——去理解并重构用户输入和数据,并决定应如何表示和处理这些操作与数据。通过允许数据系统解析、重写和分解用户输入与数据,或以超越标准的一次性查询—结果范式的方式与用户交互,数据系统能够更高效、更有效地满足用户需求。这些新能力带来了一个丰富的设计空间,使数据系统采取更多主动:它们能够基于转换操作、数据特征和用户意图执行优化。我们讨论了该框架已经以及能够如何应用于真实任务的多个成功示例,并为这一宏大研究议程提出未来方向。

英文摘要:

With the power of LLMs, we now have the ability to query data that was previously impossible to query, including text, images, and video. However, despite this enormous potential, most present-day data systems that leverage LLMs are reactive, reflecting our community's desire to map LLMs to known abstractions. Most data systems treat LLMs as an opaque black box that operates on user inputs and data as is, optimizing them much like any other approximate, expensive UDFs, in conjunction with other relational operators. Such data systems do as they are told, but fail to understand and leverage what the LLM is being asked to do (i.e. the underlying operations, which may be error-prone), the data the LLM is operating on (e.g., long, complex documents), or what the user really needs. They don't take advantage of the characteristics of the operations and/or the data at hand, or ensure correctness of results when there are imprecisions and ambiguities. We argue that data systems instead need to be proactive: they need to be given more agency -- armed with the power of LLMs -- to understand and rework the user inputs and the data and to make decisions on how the operations and the data should be represented and processed. By allowing the data system to parse, rewrite, and decompose user inputs and data, or to interact with the user in ways that go beyond the standard single-shot query-result paradigm, the data system is able to address user needs more efficiently and effectively. These new capabilities lead to a rich design space where the data system takes more initiative: they are empowered to perform optimization based on the transformation operations, data characteristics, and user intent. We discuss various successful examples of how this framework has been and can be applied in real-world tasks, and present future directions for this ambitious research agenda.

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。

↑