OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917054178656256 |
|---|---|
| author | Nayeem, Mir Tafseer Rafiei, Davood |
| author_facet | Nayeem, Mir Tafseer Rafiei, Davood |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00285 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews Nayeem, Mir Tafseer Rafiei, Davood Computation and Language Artificial Intelligence Information Retrieval 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. |
| title | OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2509.00285 |