Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations

TL;DR

Xinyu AI Search is a comprehensive generative AI search system that improves relevance, diversity, and presentation of results through query decomposition, multi-source aggregation, and innovative visualization techniques, outperforming existing methods.

Contribution

It introduces the first integrated framework combining retrieval, generation, and advanced presentation for generative AI search engines.

Findings

Outperforms eight existing search technologies in relevance and comprehensiveness.

Uses query-decomposition graph for stepwise retrieval and generation.

Enhances result presentation with timeline visualization and textual-visual choreography.

Abstract

Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, and presentation. To address these limitations, we introduce Xinyu AI Search, a novel system that incorporates a query-decomposition graph to dynamically break down complex queries into sub-queries, enabling stepwise retrieval and generation. Our retrieval pipeline enhances diversity through multi-source aggregation and query expansion, while filtering and re-ranking strategies optimize passage relevance. Additionally, Xinyu AI Search introduces a novel approach for fine-grained, precise built-in citation and innovates in result presentation by integrating timeline visualization and textual-visual choreography. Evaluated on recent real-world queries, Xinyu AI Search outperforms eight existing technologies in human assessments, excelling in relevance, comprehensiveness, and insightfulness. Ablation studies validate the necessity of its key sub-modules. Our work presents the first comprehensive framework for generative AI search engines, bridging retrieval, generation, and user-centric presentation.