OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews
This work addresses the need for user-centric summaries in review analysis, offering a scalable solution for applications like e-commerce, though it is incremental as it builds on existing RAG and LLM methods.
The paper tackled the problem of generating personalized opinion highlights from large-scale online reviews, introducing OpinioRAG, a scalable framework that achieved efficient, tailored summaries without training, and proposed novel verification metrics for sentiment-rich domains.
We study the problem of opinion highlights generation from large volumes of user reviews, often exceeding thousands per entity, where existing methods either fail to scale or produce generic, one-size-fits-all summaries that overlook personalized needs. To tackle this, we introduce OpinioRAG, a scalable, training-free framework that combines RAG-based evidence retrieval with LLMs to efficiently produce tailored summaries. Additionally, we propose novel reference-free verification metrics designed for sentiment-rich domains, where accurately capturing opinions and sentiment alignment is essential. These metrics offer a fine-grained, context-sensitive assessment of factual consistency. To facilitate evaluation, we contribute the first large-scale dataset of long-form user reviews, comprising entities with over a thousand reviews each, paired with unbiased expert summaries and manually annotated queries. Through extensive experiments, we identify key challenges, provide actionable insights into improving systems, pave the way for future research, and position OpinioRAG as a robust framework for generating accurate, relevant, and structured summaries at scale.