Multi-LLM Text Summarization
This work addresses text summarization for NLP applications, but it is incremental as it builds on existing LLM methods with multi-model strategies.
The paper tackles the problem of text summarization by proposing a multi-LLM framework with centralized and decentralized strategies, where multiple LLMs generate diverse summaries and are evaluated to select the best one, resulting in up to 3x performance improvement over single-LLM baselines.
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.