arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11581cs.IRcs.AIcs.CL
收藏

分析搜索

Analytical Search

DCST, Tsinghua University(清华大学智能驾驶与车路协同研究院);Quan Cheng Laboratory(量子工程实验室)

Yiteng Tu, Shuo Miao, Weihang Su, Yiqun Liu, Qingyao Ai

AI总结:

本文提出分析搜索范式,旨在通过证据导向和多步骤推理解决复杂分析需求,提升信息检索的端到端能力。

摘要:

分析信息需求,如趋势分析和因果影响评估,在法律、金融、科学等多个领域普遍存在。然而,现有的信息检索范式,无论是基于相关性导向的文档排序还是基于大语言模型(LLMs)的检索增强生成(RAG),往往难以满足此类任务在语料层面的端到端要求。它们要么强调信息查找而不是端到端问题解决,要么简单地将一切视为朴素的问题回答,提供有限的推理、证据使用和可验证性控制。因此,它们难以支持具有多样化实用性概念和高问责要求的分析查询。在本文中,我们提出分析搜索作为一种独特的、新兴的搜索范式,旨在满足这些分析信息需求。分析搜索将搜索重新定义为以证据为导向、以过程为导向的分析工作流程,明确建模分析意图,检索证据以融合,并通过结构化、多步骤推理生成可验证的结论。我们将分析搜索与现有范式对立,并提出一个统一的系统框架,整合查询理解、以召回为导向的检索、推理感知的融合以及自适应验证。我们还讨论了构建分析搜索引擎的潜在研究方向。通过这种方式,我们强调了分析搜索的概念意义和实际重要性,并呼吁努力构建支持分析信息需求的下一代搜索引擎。

英文摘要:

Analytical information needs, such as trend analysis and causal impact assessment, are prevalent across various domains including law, finance, science, and much more. However, existing information retrieval paradigms, whether based on relevance-oriented document ranking or retrieval-augmented generation (RAG) with large language models (LLMs), often struggle to meet the end-to-end requirements of such tasks at the corpus scale. They either emphasize information finding rather than end-to-end problem solving, or simply treat everything as naive question answering, offering limited control over reasoning, evidence usage, and verifiability. As a result, they struggle to support analytical queries that have diverse utility concepts and high accountability requirements. In this paper, we propose analytical search as a distinct and emerging search paradigm designed to fulfill these analytical information needs. Analytical search reframes search as an evidence-governed, process-oriented analytical workflow that explicitly models analytical intent, retrieves evidence for fusion, and produces verifiable conclusions through structured, multi-step inference. We position analytical search in contrast to existing paradigms, and present a unified system framework that integrates query understanding, recall-oriented retrieval, reasoning-aware fusion, and adaptive verification. We also discuss potential research directions for the construction of analytical search engines. In this way, we highlight the conceptual significance and practical importance of analytical search and call on efforts toward the next generation of search engines that support analytical information needs.

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。

↑