Multi-LLM Text Summarization

TL;DR

This paper introduces a multi-LLM summarization framework with centralized and decentralized strategies, demonstrating significant improvements over single-LLM methods in generating high-quality summaries.

Contribution

The paper presents a novel multi-LLM summarization framework with two strategies, showing how multiple LLMs can be coordinated for better summarization results.

Findings

Multi-LLM approaches outperform single LLM baselines by up to 3x.

Decentralized and centralized strategies have different evaluation mechanisms.

Multi-LLM methods significantly improve summary quality.

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.