Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.21849 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912399426060288 |
|---|---|
| author | Tang, Bo Zhu, Junyi Xi, Chenyang Ge, Yunhang Wu, Jiahao Feng, Yuchen Niu, Yijun Wei, Wenqiang Yu, Yu Li, Chunyu Lin, Zehao Wu, Hao Liao, Ning Yang, Yebin Wang, Jiajia Li, Zhiyu Xiong, Feiyu Chen, Jingrun |
| author_facet | Tang, Bo Zhu, Junyi Xi, Chenyang Ge, Yunhang Wu, Jiahao Feng, Yuchen Niu, Yijun Wei, Wenqiang Yu, Yu Li, Chunyu Lin, Zehao Wu, Hao Liao, Ning Yang, Yebin Wang, Jiajia Li, Zhiyu Xiong, Feiyu Chen, Jingrun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21849 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations Tang, Bo Zhu, Junyi Xi, Chenyang Ge, Yunhang Wu, Jiahao Feng, Yuchen Niu, Yijun Wei, Wenqiang Yu, Yu Li, Chunyu Lin, Zehao Wu, Hao Liao, Ning Yang, Yebin Wang, Jiajia Li, Zhiyu Xiong, Feiyu Chen, Jingrun Information Retrieval Artificial Intelligence 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. |
| title | Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2505.21849 |