用图像描述提升生成式搜索内容可见性，让多模态信息更好被用户感知。
Caption Injection for Optimization in Generative Search Engine
- 从图像中提取描述文本并注入到搜索结果中，融合视觉语义增强内容感知。
- 在多模态基准上测试，相比纯文本优化方法，主观可见性提升显著。
- 首个多模态生成式搜索优化方案，适合关注生成式搜索与多模态融合的研究者。
生成式搜索引擎（GSE）利用检索增强生成（RAG）技术和大语言模型（LLM），整合多源信息，为用户提供准确且全面的回答。与传统搜索引擎按排序列表展示结果不同，GSE将用户注意力从逐条浏览转向内容驱动的主观感知，推动信息检索范式变革，并凸显提升生成式搜索中内容主观可见性的重要性。在此背景下，生成式搜索引擎优化（G-SEO）成为新研究焦点。随着多模态检索增强生成（MRAG）技术快速发展，GSE now 可高效融合文本、图像、音频和视频，生成更丰富的响应以满足复杂信息需求。然而，现有G-SEO方法仍局限于文本优化，未能充分利用多模态数据。为此，我们提出首个多模态G-SEO方法——Caption Injection，通过提取图像中的字幕并注入文本内容，融入视觉语义以增强生成搜索中的主观可见性。我们在MRAMG这一多模态RAG基准上，于单模态与多模态设置下系统评估该方法。实验结果表明，Caption Injection在G-EVAL指标上显著优于仅基于文本的G-SEO基线，有效提升了用户对内容的主观感知可见性，验证了多模态信息在G-SEO中的实际价值。代码已开源：https://github.com/GrayChan04/Caption-Injection。
原文摘要 · Abstract (English)
Generative Search Engine (GSE) leverages the Retrieval-Augmented Generation (RAG) technique and the Large Language Model (LLM) to integrate multi-source information and provide users with accurate and comprehensive responses. Unlike traditional search engines that present results in ranked lists, GSE shifts users' attention from sequential browsing to content-driven subjective perception, not only driving a paradigm shift in information retrieval but also highlighting the importance of enhancing the subjective visibility of content in generative search. In this context, Generative Search Engine Optimization (G-SEO) methods have emerged as a new research focus. With the rapid advancement of Multimodal Retrieval-Augmented Generation (MRAG) techniques, GSE can now efficiently integrate text, images, audio, and video, producing richer responses that better satisfy complex information needs. Existing G-SEO methods, however, remain limited to text-based optimization and fail to fully exploit multimodal data. To address this gap, we propose Caption Injection, the first multimodal G-SEO approach, which extracts captions from images and injects them into textual content, integrating visual semantics to enhance the subjective visibility in generative search. We systematically evaluate Caption Injection on MRAMG, a benchmark for MRAG, under both unimodal and multimodal settings. Experimental results show that Caption Injection significantly outperforms text-only G-SEO baselines under the G-EVAL metric, effectively improving the subjective visibility of content perceived by users, and demonstrating the practical benefits of multimodal information in G-SEO. The source code for this work is openly available at https://github.com/GrayChan04/Caption-Injection.
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。