Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective

TL;DR

This paper evaluates various large language models for real-world meeting summarization, highlighting that smaller open-source models like LLaMA-2 can achieve performance comparable to larger closed-source models, offering practical benefits for industry.

Contribution

The paper provides a comprehensive comparison of open-source and closed-source LLMs for meeting summarization, emphasizing the practicality of open models like LLaMA-2 for industrial applications.

Findings

Closed-source LLMs generally outperform open-source models.

LLaMA-2-7B achieves comparable performance to larger models.

Open-source models offer cost-effective and privacy-preserving alternatives.

Abstract

This paper studies how to effectively build meeting summarization systems for real-world usage using large language models (LLMs). For this purpose, we conduct an extensive evaluation and comparison of various closed-source and open-source LLMs, namely, GPT-4, GPT- 3.5, PaLM-2, and LLaMA-2. Our findings reveal that most closed-source LLMs are generally better in terms of performance. However, much smaller open-source models like LLaMA- 2 (7B and 13B) could still achieve performance comparable to the large closed-source models even in zero-shot scenarios. Considering the privacy concerns of closed-source models for only being accessible via API, alongside the high cost associated with using fine-tuned versions of the closed-source models, the opensource models that can achieve competitive performance are more advantageous for industrial use. Balancing performance with associated costs and privacy concerns, the LLaMA-2-7B model looks more promising for industrial usage. In sum, this paper offers practical insights on using LLMs for real-world business meeting summarization, shedding light on the trade-offs between performance and cost.