让搜索结果既相关又可信，用权威性提升生成式检索质量
From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines
- 引入视觉语言模型综合图文信息评估文档权威性
- 3B模型在权威性和准确率上媲美14B大模型
- 适合对信息可靠性要求高的医疗金融等场景
生成式信息检索（GenIR）将检索过程视为文本到文本的生成任务，利用大语言模型的丰富知识。然而，现有方法主要优化相关性，常忽视文档可信度。在医疗、金融等高风险领域，仅依赖语义相关性可能引入不可靠信息。为此，我们提出首个融入权威性的生成式检索框架AuthGR。该框架包含三部分：(i) 多模态权威评分，采用视觉语言模型从文本和图像中量化权威性；(ii) 三阶段训练流程，逐步注入权威意识；(iii) 混合集成部署策略，确保鲁棒性。离线评估显示，AuthGR显著提升权威性和准确性，3B模型表现媲美14B基线。关键的是，大规模在线A/B测试与人工评估在商用搜索引擎上验证了用户参与度与信息可靠性的明显提升。
原文摘要 · Abstract (English)
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.
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。