Xinyu AI搜索通过拆解复杂问题，实现更准更全的答案呈现。
Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
- 用查询图动态拆解复杂问题，分步检索生成答案
- 在真实查询上优于8种现有技术，综合表现更优
- 支持时间线可视化和图文协同展示，提升可读性
传统搜索引擎难以整合碎片信息应对复杂查询，而生成式AI搜索又面临相关性、全面性和呈现方式的挑战。为此，我们提出Xinyu AI Search，引入查询分解图，动态将复杂查询拆分为子查询，实现分步检索与生成。检索管道通过多源聚合与查询扩展增强多样性，结合过滤与重排序策略优化段落相关性。系统还提出细粒度精准引用机制，并创新结果呈现方式，融合时间线可视化与文本-视觉编排。在近期真实查询上的评估显示，Xinyu AI Search在人类评价中超越八种现有技术，在相关性、全面性和洞察力方面表现突出。消融实验验证了关键模块的必要性。本工作首次构建了面向生成式AI搜索的完整框架，贯通检索、生成与用户友好呈现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。