# MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering

arXiv: https://arxiv.org/abs/2603.19277 · HTML: https://mlsanity.com/paper/2603.19277/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators](https://mlsanity.com/paper/2403.16950/) (2024)
- [Extractive Opinion Summarization in Quantized Transformer Spaces](https://mlsanity.com/paper/2012.04443/) (2020)
- [Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised](https://mlsanity.com/paper/1808.08858/) (2018)
- [Unsupervised Opinion Summarization as Copycat-Review Generation](https://mlsanity.com/paper/1911.02247/) (2019)
- [Aspect-Controllable Opinion Summarization](https://mlsanity.com/paper/2109.03171/) (2021)
- [Neural Network-Based Abstract Generation for Opinions and Arguments](https://mlsanity.com/paper/1606.02785/) (2016)
- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [Unsupervised Opinion Summarization with Noising and Denoising](https://mlsanity.com/paper/2004.10150/) (2020)
- [OpinionDigest: A Simple Framework for Opinion Summarization](https://mlsanity.com/paper/2005.01901/) (2020)
- [Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation](https://mlsanity.com/paper/2305.01498/) (2023)
- [Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking](https://mlsanity.com/paper/1906.05691/) (2019)
- [A Sentiment Consolidation Framework for Meta-Review Generation](https://mlsanity.com/paper/2402.18005/) (2024)
- [M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2502.11824/) (2025)
- [Hierarchical Indexing for Retrieval-Augmented Opinion Summarization](https://mlsanity.com/paper/2403.00435/) (2024)
- [Prompted Aspect Key Point Analysis for Quantitative Review Summarization](https://mlsanity.com/paper/2407.14049/) (2024)
- [HDBSCAN: Density based Clustering over Location Based Services](https://mlsanity.com/paper/1602.03730/) (2016)
- [Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder](https://mlsanity.com/paper/2004.05755/) (2020)
- [Decomposed Opinion Summarization with Verified Aspect-Aware Modules](https://mlsanity.com/paper/2501.17191/) (2025)
- [Aspect-Based Opinion Summarization with Argumentation Schemes](https://mlsanity.com/paper/2506.09917/) (2025)

## Abstract (arXiv)

Reviews are central to how travelers evaluate products on online marketplaces, yet existing summarization research often emphasizes end-to-end quality while overlooking benchmark reliability and the practical utility of granular insights. To address this, we propose MOSAIC, a scalable, modular framework designed for industrial deployment that decomposes summarization into interpretable components, including theme discovery, structured opinion extraction, and grounded summary generation. We validate the practical impact of our approach through online A/B tests on live product pages, showing that surfacing intermediate outputs improves customer experience and delivers measurable value even prior to full summarization deployment. We further conduct extensive offline experiments to demonstrate that MOSAIC achieves superior aspect coverage and faithfulness compared to strong baselines for summarization. Crucially, we introduce opinion clustering as a system-level component and show that it significantly enhances faithfulness, particularly under the noisy and redundant conditions typical of user reviews. Finally, we identify reliability limitations in the standard SPACE dataset and release a new open-source tour experience dataset (TRECS) to enable more robust evaluation.