在基于大语言模型的搜索生成引擎中控制输出排名
Controlling Output Rankings in LLM-Based Search via Generative Engine Optimization
AI总结：
CORE通过优化内容生成，提升基于LLM的搜索中小企业产品的可见性，实现高推广成功率。
摘要：
随着大语言模型（LLMs）的兴起，客户寻找和选择产品的方式正在发生变化。基于LLM的搜索，或生成引擎，能够直接向用户提供产品推荐，而不是传统的在线搜索结果，后者需要用户自行探索选项。然而，这些推荐受到LLM初始检索顺序的强烈影响，这会不利地影响小企业和独立创作者的可见性。在本工作中，我们提出了CORE，一种优化方法，通过在生成引擎中控制输出排名来优化检索内容。由于LLM与搜索引擎的交互是黑箱的，CORE以搜索引擎返回的内容作为主要影响输出排名的手段。具体而言，CORE通过附加战略性设计的优化内容来优化检索内容，以引导输出的排名。我们引入了三种类型的优化内容：基于字符串的、基于推理的和基于评论的，展示了它们在塑造输出排名中的有效性。为了在现实环境中评估CORE，我们引入了ProductBench，一个包含15个产品类别和每个类别200个产品的大型基准测试，其中每个产品都与其从Amazon搜索界面收集的前10条推荐相关联。在四个具有搜索能力的LLM（GPT-4o、Gemini-2.5、Claude-4和Grok-3）上进行的大量实验表明，CORE在15个产品类别上实现了平均推广成功率分别为Top-5 91.4%、Top-3 86.6%和Top-1 80.3%，优于现有排名操控方法，同时保持了优化内容的流畅性。
英文摘要：
The way customers search for and choose products is changing with the rise of large language models (LLMs). LLM-based search, or generative engines, provides direct product recommendations to users, rather than traditional online search results that require users to explore options themselves. However, these recommendations are strongly influenced by the initial retrieval order of LLMs, which disadvantages small businesses and independent creators by limiting their visibility. In this work, we propose CORE, an optimization method that \textbf{C}ontrols \textbf{O}utput \textbf{R}ankings in g\textbf{E}nerative Engines for LLM-based search. Since the LLM's interactions with the search engine are black-box, CORE targets the content returned by search engines as the primary means of influencing output rankings. Specifically, CORE optimizes retrieved content by appending strategically designed optimization content to steer the ranking of outputs. We introduce three types of optimization content: string-based, reasoning-based, and review-based, demonstrating their effectiveness in shaping output rankings. To evaluate CORE in realistic settings, we introduce ProductBench, a large-scale benchmark with 15 product categories and 200 products per category, where each product is associated with its top-10 recommendations collected from Amazon's search interface. Extensive experiments on four LLMs with search capabilities (GPT-4o, Gemini-2.5, Claude-4, and Grok-3) demonstrate that CORE achieves an average Promotion Success Rate of \textbf{91.4\% @Top-5}, \textbf{86.6\% @Top-3}, and \textbf{80.3\% @Top-1}, across 15 product categories, outperforming existing ranking manipulation methods while preserving the fluency of optimized content.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
