In this work, we propose a Multi-LLM summarization framework, and investigate two different multi-LLM strategies including centralized and decentralized. Our multi-LLM summarization framework has two fundamentally important steps at each round of conversation: generation and evaluation. These steps are different depending on whether our multi-LLM decentralized summarization is used or centralized. In both our multi-LLM decentralized and centralized strategies, we have k different LLMs that generate diverse summaries of the text. However, during evaluation, our multi-LLM centralized summarization approach leverages a single LLM to evaluate the summaries and select the best one whereas k LLMs are used for decentralized multi-LLM summarization. Overall, we find that our multi-LLM summarization approaches significantly outperform the baselines that leverage only a single LLM by up to 3x. These results indicate the effectiveness of multi-LLM approaches for summarization.
@article{arxiv.2412.15487,
title = {Multi-LLM Text Summarization},
author = {Jiangnan Fang and Cheng-Tse Liu and Jieun Kim and Yash Bhedaru and Ethan Liu and Nikhil Singh and Nedim Lipka and Puneet Mathur and Nesreen K. Ahmed and Franck Dernoncourt and Ryan A. Rossi and Hanieh Deilamsalehy},
journal= {arXiv preprint arXiv:2412.15487},
year = {2025}
}