"This Suits You the Best": Query Focused Comparative Explainable Summarization
By: Arnav Attri , Anuj Attri , Pushpak Bhattacharyya and more
Potential Business Impact:
Helps shoppers compare products with clear reasons.
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.
Similar Papers
LLMs as Architects and Critics for Multi-Source Opinion Summarization
Computation and Language
Summaries tell you more about products.
Query-Focused Extractive Summarization for Sentiment Explanation
Computation and Language
Helps understand why people feel a certain way.
QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering
Computation and Language
Answers questions using many customer opinions.