让推荐总结更懂用户提问，自动对比产品并解释理由。
"This Suits You the Best": Query Focused Comparative Explainable Summarization
- 用多源评论生成查询聚焦的对比摘要，支持个性化推荐
- 相较直接处理原始数据，推理延迟降低约40%
- 适合需要精准推荐解释的电商与内容平台
产品推荐本质上涉及对比，但传统意见摘要难以提供全面的比较洞察。我们提出生成查询聚焦的对比可解释摘要（QF-CES）的新任务，采用多源意见摘要（M-OS）方法。为解决查询聚焦推荐数据集缺乏的问题，我们构建了包含7,500个查询、映射至22,500个推荐产品的MS-Q2P数据集，附带元数据。利用大语言模型（LLMs）生成带有查询特定解释的表格化对比摘要。该方法具有个性化、隐私保护、不依赖推荐引擎和类别无关的优点。以M-OS作为中间步骤，相比直接输入方法（DIA），推理延迟降低约40%。我们在开源和专有LLM上评估了生成与评估QF-CES的能力。通过在五个维度（清晰度、忠实性、信息量、格式符合度、查询相关性）使用QF-CES-PROMPT进行评估，结果显示与人工判断的平均斯皮尔曼相关系数为0.74，表明其在评估QF-CES方面的潜力。
原文摘要 · Abstract (English)
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.
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。