Analytical Search
Yiteng Tu, Shuo Miao, Weihang Su, Yiqun Liu, Qingyao Ai
TL;DR
This paper defines analytical information needs and introduces analytical search, a paradigm that treats search as evidence-grounded, end-to-end analytical problem solving rather than pure information retrieval. It presents a conceptual framework with four interacting modules—Query, Retrieval, Fusion, and Verification—and demonstrates an end-to-end example to illustrate module interactions and the shift from surface relevance to verifiable, reasoning-based conclusions. It outlines research directions across sequential reasoning, recall-oriented retrieval, dynamic indexing, and evaluation principles, emphasizing verifiability, traceability, and efficiency. By unifying IR, NLP, and database concepts, analytical search aims to support high-stakes analytical tasks across domains and invites the IR community to develop robust, scalable implementations.
Abstract
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.