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.

Here are 5 books I've read recently that I thought were excellent and definitely worth any AI person's time… One of the books isn't even on AI, but I think the topic should be required for many practitioners and thought leaders. I first read this book a few years ago when it was published, and I find myself coming back to it as a reference every few months when I need to make sure I'm understanding a concept or need to double check mine or someone else's work. It's an excellent summary to theory and concepts for someone who wants a little deeper understanding. I think a great route to learning and getting a moderately deep theoretical and practical understanding is to go piece by piece through this text and the next text "Deep Learning with Python" simultaneously. Try to push through a chapter of theory and understand at least the basics of the chapter in "Deep Learning" and then go build these ideas using a corresponding chapter from "Deep Learning with Python."