用点击率引导生成更符合用户偏好的对话搜索查询建议。
CTR-Guided Generative Query Suggestion in Conversational Search
- 结合点击率建模与偏好优化，生成更贴近用户兴趣的查询建议。
- 在真实数据上提升点击率、相关性与多样性，优于现有方法。
- 适合需要高精度搜索推荐的平台，如电商或搜索引擎。
在对话式搜索中生成有效的查询建议，需使模型输出与用户偏好对齐，但稀疏且嘈杂的点击信号带来了挑战。我们提出GQS，一种整合点击率建模与偏好优化的生成框架，以提升实际用户参与度。GQS包含三个核心组件：(1) 多源点击率建模模块，捕捉多样化上下文信号，估算细粒度点击通过率；(2) 基于点击率加权的直接偏好优化（CTR-weighted DPO）的多样性感知偏好对齐策略，平衡相关性与语义多样性；(3) 点击率校准的迭代优化过程，在训练轮次中联合优化点击率与生成模型。在两个真实任务上的实验表明，GQS在点击率、相关性与多样性上均优于强基线。
原文摘要 · Abstract (English)
Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. We propose GQS, a generative framework that integrates click modeling and preference optimization to enhance real-world user engagement. GQS consists of three key components: (1) a Multi-Source CTR Modeling module that captures diverse contextual signals to estimate fine-grained click-through rates; (2) a Diversity-Aware Preference Alignment strategy using CTR-weighted Direct Preference Optimization (DPO), which balances relevance and semantic diversity; and (3) a CTR-Calibrated Iterative Optimization process that jointly refines the CTR and generation models across training rounds. Experiments on two real-world tasks demonstrate that GQS outperforms strong baselines in CTR, relevance, and diversity.
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。