用多个大模型协作生成更优摘要，效果最高提升3倍。
Multi-LLM Text Summarization
- 多模型协同生成+评估，分集中与分散两种策略。
- 相比单模型，摘要质量最高提升3倍，显著优于基线。
- 适合需要高质量摘要的场景，如科研文献精读。
本文提出一种多大模型文本摘要框架，探索集中式与去中心化两种多模型策略。每轮对话包含生成与评估两个核心步骤，策略不同则流程各异。两种方法均使用k个不同大模型生成多样化摘要；集中式由单一模型评估并筛选最优，去中心化则由k个模型共同评估。实验表明，多模型方法相较仅使用单个大模型的基线，摘要性能最高提升3倍，验证了多模型协同在摘要任务中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。