生成式搜尋引擎的偏好與網頁內容的協同優化策略

摘要

通過運用大型語言模型（LLMs）來檢索文件並生成自然語言回應，生成式引擎（如Google AI概覽和ChatGPT）提供了顯著提升的用戶體驗，並迅速成為搜索的新形式。它們的快速普及也推動了生成式引擎優化（GEO）的需求，因為內容提供者渴望從中獲得更多關注。在本文中，我們介紹了AutoGEO，這是一個框架，用於在使用檢索內容生成回應時自動學習生成式引擎的偏好，並重寫網絡內容以獲得更多此類關注。AutoGEO首先提示前沿的LLMs解釋生成式引擎的偏好，並從這些解釋中提取有意義的偏好規則。然後，它將這些偏好規則用作AutoGEO_API（一個基於提示的GEO系統）的上下文工程，並作為基於規則的獎勵來訓練AutoGEO_Mini（一個成本效益高的GEO模型）。在標準的GEO-Bench和兩個新構建的基準上使用真實用戶查詢進行的實驗證明了AutoGEO在增強內容關注度同時保持搜索效用方面的有效性。分析確認了學習到的規則的穩健性及其在捕捉不同領域獨特偏好方面的能力，以及AutoGEO系統在內容優化中嵌入這些規則的能力。代碼已發佈於https://github.com/cxcscmu/AutoGEO。

English

By employing large language models (LLMs) to retrieve documents and generate natural language responses, Generative Engines, such as Google AI overview and ChatGPT, provide significantly enhanced user experiences and have rapidly become the new form of search. Their rapid adoption also drives the needs of Generative Engine Optimization (GEO), as content providers are eager to gain more traction from them. In this paper, we introduce AutoGEO, a framework to automatically learn generative engine preferences when using retrieved contents for response generation, and rewrite web contents for more such traction. AutoGEO first prompts frontier LLMs to explain generative engine preferences and extract meaningful preference rules from these explanations. Then it uses preference rules as context engineering for AutoGEO_API, a prompt-based GEO system, and as rule-based rewards to train AutoGEO_Mini, a cost-effective GEO model. Experiments on the standard GEO-Bench and two newly constructed benchmarks using real user queries demonstrate the effectiveness of AutoGEO in enhancing content traction while preserving search utility. Analyses confirm the learned rules' robustness and abilities to capture unique preferences in variant domains, and AutoGEO systems' ability to embed them in content optimization. The code is released at https://github.com/cxcscmu/AutoGEO.

生成式搜尋引擎的偏好與網頁內容的協同優化策略

What Generative Search Engines Like and How to Optimize Web Content Cooperatively

摘要

Support