从相关性到权威性：面向网页搜索引擎的权威感知生成检索
From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines
AI总结：
本文提出权威感知生成检索框架AuthGR，通过多模态权威评分、三阶段训练和混合集成流程提升检索的权威性和准确性，在实际应用中显著提高用户参与度和可靠性。
摘要：
生成信息检索（GenIR）将检索过程建模为文本到文本的生成任务，利用大语言模型的广泛知识。然而，现有方法主要优化相关性而忽视文档可信度。在医疗和金融等高风险领域，仅依赖语义相关性可能检索到不可靠信息。为此，我们提出权威感知生成检索器（AuthGR），是首个将权威纳入GenIR的框架。AuthGR包含三个关键组件：（i）多模态权威评分，利用视觉语言模型量化文本和视觉线索的权威性；（ii）三阶段训练流程逐步灌输权威意识；（iii）混合集成流程实现稳健部署。离线评估显示，AuthGR在权威性和准确性上均得到提升，我们的3B模型可与14B基线相媲美。关键的是，大规模在线A/B测试和商业搜索引擎平台的人类评估证实了在现实世界中用户参与度和可靠性显著提升。
英文摘要：
Generative information retrieval (GenIR) formulates the retrieval process as a text-to-text generation task, leveraging the vast knowledge of large language models. However, existing works primarily optimize for relevance while often overlooking document trustworthiness. This is critical in high-stakes domains like healthcare and finance, where relying solely on semantic relevance risks retrieving unreliable information. To address this, we propose an Authority-aware Generative Retriever (AuthGR), the first framework that incorporates authority into GenIR. AuthGR consists of three key components: (i) Multimodal Authority Scoring, which employs a vision-language model to quantify authority from textual and visual cues; (ii) a Three-stage Training Pipeline to progressively instill authority awareness into the retriever; and (iii) a Hybrid Ensemble Pipeline for robust deployment. Offline evaluations demonstrate that AuthGR successfully enhances both authority and accuracy, with our 3B model matching a 14B baseline. Crucially, large-scale online A/B tests and human evaluations conducted on the commercial web search platform confirm significant improvements in real-world user engagement and reliability.
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。
