Products
Developers
About

THE BENEFITS OF
LARGE LANGUAGE MODELS
FOR DOCUMENT
CLASSIFICATION

Large Language Models have been popular in the AI and deep learning communities because of their ability to solve a wide range of tasks with just a single model. However, to understand how these large models work, we need to understand their tasks. This demo will show how the increased sequence length of SambaNova GPT results in higher accuracy of classifying long form documents such as customer emails.

The challenge:
Manual review of customer support emails

Email is one of the highest volume customer engagement channels for many organizations. Customers email businesses to ask billing questions, buy new products, register complaints, and understand details about their account. Often these emails are sent to a centralized email address:

info, support, or something similar, and need to be routed to the correct team for action to be taken, consuming anywhere from 2-5 minutes per email for an agent to manually review. This can create a bottleneck in resolving critical issues, lowering customer satisfaction, and increasing costs.

The solution:

AI-driven email routing

AI-driven email routing

AI can address this bottleneck by analyzing emails to understand their context and intent, then automatically forward them to the correct department for resolution. However, large language models can determine this with greater accuracy than smaller models, such as BERT. One way in which a large language model like GPT can better solve this by utilizing a larger sequence length. Sequence length refers to the ability to analyze more information from the document at once, to generate better context and understanding.

To understand how this works in the real world, try the GPT Challenge below:

1
Select an email sample
2
Read through it in 5 seconds
3
Cast in your vote

Talk to an Expert

Learn how SambaNova can advance your AI initiatives to help you achieve your impossible.
Get Started