RAID：面向生成式搜索引擎优化的角色增强意图驱动方法
Role-Augmented Intent-Driven Generative Search Engine Optimization
AI 导读
论文提出 RAID，一种无需访问目标查询及查询相关 GSE 反馈的生成式搜索引擎优化（G-SEO）方法，从源内容推断检索主意图，经 4W 多角色深度反思细化后规划并重写内容。
正文 · 原文
Abstract:Generative search engines (GSEs), which combine large language models (LLMs) with retrieval-augmented generation (RAG), are reshaping how users access Web information and making source visibility and influence in generated responses new optimization objectives. Existing generative search engine optimization (G-SEO) methods seek to improve content visibility, but many rely on direct access to target queries or GSE feedback elicited by those queries. However, Web content is typically optimized and published before future user queries are known, making G-SEO without access to target queries or their associated feedback an important yet underexplored problem. To address this, we propose RAID, a Role-Augmented Intent-Driven G-SEO method that operates without access to target queries or query-dependent GSE feedback. RAID infers a primary retrieval intent from source content, refines it through 4W multi-role deep reflection on prospective searchers' information needs, and uses both the primary and refined intents to jointly plan and rewrite source content. We further extend GEO-BENCH with diverse topic-related query variants, using both the original queries and their variants exclusively for evaluation to assess generalization to queries unseen during optimization. Across 100 samples and 500 evaluation queries, RAID achieves Relative Improvement Scores (RIS) of 3.00\% for Objective Overall and 1.32\% for Subjective Average, exceeding the best corresponding results among the nine predefined GEO rewriting strategies by 1.31 and 0.74 percentage points, respectively. With an optimization considered effective when $\mathrm{RIS}>0$, its effective optimization rates for Objective Overall and Subjective Average average 58.0\%, exceeding the highest corresponding average among the predefined strategies by 4.5 percentage points.
| Comments: | 12 pages, 5 figures, 9 tables |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2508.11158 [cs.IR] |
| (or arXiv:2508.11158v3 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2508.11158 arXiv-issued DOI via DataCite |
Submission history
From: Xiaolu Chen [view email]
[v1]
Fri, 15 Aug 2025 02:08:55 UTC (553 KB)
[v2]
Wed, 18 Mar 2026 13:12:31 UTC (1,829 KB)
[v3]
Tue, 27 Oct 2026 09:58:45 UTC (2,851 KB)
来源：arXiv cs.AI · arxiv.org