@inproceedings{fang-etal-2025-multi,
    title = "Multi-{LLM} Text Summarization",
    author = "Fang, Jiangnan  and
      Liu, Cheng-Tse  and
      Kim, Jieun  and
      Bhedaru, Yash  and
      Liu, Ethan  and
      Singh, Nikhil  and
      Lipka, Nedim  and
      Mathur, Puneet  and
      Ahmed, Nesreen K.  and
      Dernoncourt, Franck  and
      Rossi, Ryan  and
      Deilamsalehy, Hanieh",
    editor = "Angelova, Galia  and
      Kunilovskaya, Maria  and
      Escribe, Marie  and
      Mitkov, Ruslan",
    booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/corrections-2026-01/2025.ranlp-1.43/",
    pages = "352--362",
    abstract = "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."
}