“这最适合你”：面向查询的比较式可解释摘要生成
"This Suits You the Best": Query Focused Comparative Explainable Summarization
AI总结：
本文提出面向查询的比较式可解释摘要生成任务QF-CES，引入MS-Q2P数据集，并利用多源观点摘要作为中间步骤结合大语言模型生成表格化比较摘要，在降低推理延迟的同时实现了与人类判断高度相关的评估效果。
摘要：
产品推荐本质上涉及比较，然而传统的观点摘要往往无法提供整体性的比较洞察。我们提出了一项新任务：利用多源观点摘要（M-OS）生成面向查询的比较式可解释摘要（QF-CES）。为解决缺乏面向查询的推荐数据集这一问题，我们引入了MS-Q2P数据集，其中包含7,500个查询，映射到22,500个带有元数据的推荐产品。我们利用大语言模型（LLMs）生成带有查询特定解释的表格化比较摘要。我们的方法具有个性化、隐私保护、推荐引擎无关和类别无关的特点。与直接处理原始数据的直接输入方法（DIA）相比，将M-OS作为中间步骤可将推理延迟降低约40%。我们评估了开源和专有LLMs在生成和评估QF-CES方面的表现。使用QF-CES-PROMPT在5个维度（清晰性、忠实性、信息量、格式符合性和查询相关性）上进行的大量评估显示，与人类判断的平均Spearman相关系数为0.74，表明其在QF-CES评估方面具有潜力。
英文摘要：
Product recommendations inherently involve comparisons, yet traditional opinion summarization often fails to provide holistic comparative insights. We propose the novel task of generating Query-Focused Comparative Explainable Summaries (QF-CES) using Multi-Source Opinion Summarization (M-OS). To address the lack of query-focused recommendation datasets, we introduce MS-Q2P, comprising 7,500 queries mapped to 22,500 recommended products with metadata. We leverage Large Language Models (LLMs) to generate tabular comparative summaries with query-specific explanations. Our approach is personalized, privacy-preserving, recommendation engine-agnostic, and category-agnostic. M-OS as an intermediate step reduces inference latency approximately by 40% compared to the direct input approach (DIA), which processes raw data directly. We evaluate open-source and proprietary LLMs for generating and assessing QF-CES. Extensive evaluations using QF-CES-PROMPT across 5 dimensions (clarity, faithfulness, informativeness, format adherence, and query relevance) showed an average Spearman correlation of 0.74 with human judgments, indicating its potential for QF-CES evaluation.
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。
