# Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization

arXiv: https://arxiv.org/abs/2607.10825 · HTML: https://mlsanity.com/paper/2607.10825/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Text Classification via Large Language Models](https://mlsanity.com/paper/2305.08377/) (2023)
- [LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K](https://mlsanity.com/paper/2402.05136/) (2024)
- [A Literature Survey of Recent Advances in Chatbots](https://mlsanity.com/paper/2201.06657/) (2022)
- [Automatic Text Summarization Methods: A Comprehensive Review](https://mlsanity.com/paper/2204.01849/) (2022)
- [Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets](https://mlsanity.com/paper/2310.13340/) (2023)
- [Beyond Opinion Mining: Summarizing Opinions of Customer Reviews](https://mlsanity.com/paper/2206.01543/) (2022)
- [Mining customer product reviews for product development: A summarization process](https://mlsanity.com/paper/2001.04200/) (2020)
- [Coverage-based Fairness in Multi-document Summarization](https://mlsanity.com/paper/2412.08795/) (2024)

## Abstract (arXiv)

Opinionated text - spanning product reviews, hotel feedback, and social posts - captures rich signals about user experiences, preferences, and concerns. However, the scale, redundancy, and imbalance of such corpora make it challenging to analyze opinions effectively, particularly when the goal is to generate summaries that remain faithful to the diversity of viewpoints expressed. This paper presents a framework that preserves semantics in LLM-based opinion summarization while minimizing token usage. We combine multidimensional classification (e.g., sentiment, topics) with a family of stratified sampling strategies to select compact yet representative subsets of opinions before prompting the LLM. Tailored prompts then produce balanced summaries that surface the salient aspects expressed in the opinions (e.g., strengths and weaknesses of products/hotels). Experiments on Amazon product reviews, Tripadvisor hotel reviews, and X/Twitter posts demonstrate that our method significantly reduces token usage and computational cost while consistently outperforming traditional AI-based and standard LLM summarization baselines in terms of content coverage, balance, and semantic preservation.