Progressive retrieval improves complex question answering from multiple web pages
PCG-RAG: Progressive Compositional Grounding for Retrieval-Augmented Generation in Complex Web Question Answering
Information Retrieval
Summary
Answering complex questions from the web is hard because clues are scattered across many long pages, and no single page usually has all the information needed. The authors propose a new method that first finds partial clues and uses them to guide further searches, gradually collecting all the needed evidence before answering. Their approach keeps track of partial answers and refines them step-by-step to avoid getting distracted by incomplete information. This method works better than previous ones, showing notable improvements on challenging web question datasets.
What this means in practice
- •For search engine developers: build search engines that answer complex user questions by combining clues from multiple web pages more accurately.$Commercial implications: Creates improved AI-powered question answering features for search engines that combine multi-page information, enhancing user experience.
- •For ai assistant developers: enable AI assistants to retrieve and compose evidence from diverse web documents to answer detailed and multi-step questions more reliably.
Authors
Linyao Zheng, Xuhang Shi, Zhifang Mao, Chongqi Qu, Xiuquan Hou
Abstract
Complex Web question answering requires retrieval-augmented generation (RAG) systems to identify target entities from multi-clue descriptions and connect evidence scattered across long Web pages. Individual pages often support only some of the required semantic constraints, while clues discovered on one page guide subsequent searches on others. However, premature reliance on partially supported entity hypotheses can divert retrieval from the original information need. RAG systems must therefore use partial evidence to guide further searches while seeking the evidence needed to establish the intended entities. We propose PCG-RAG, a novel RAG framework based on Progressive Compositional Grounding (PCG). Progressive Evidence Acquisition directs subsequent searches toward missing evidence for candidate attributes and relations. Compositional Reasoning separates candidate-guided retrieval from evidence-based answering along a directed acyclic graph (DAG) of subquestions. Provisional names make dependent searches specific, while answering tasks use accepted results and unresolved identifying conditions, assessed against the original question. New passages connect the identifying clues to the requested relations, supporting evidence-based downstream answers. Evidence Grounding combines identifying and relational source passages with supported intermediate answers, connecting evidence across Web pages to the original conditions during final generation. On BrowseComp-Plus and WebWalkerQA, PCG-RAG improves accuracy over the leading compared baselines by 5.43 and 5.15 percentage points, respectively.