📢 Announcing Refuel — and our $5.2M fundraise led by General Catalyst 📢
Company
About Us
Careers
HomeAbout UsCareersBlogDocsGithubDiscordSchedule a Demo

Refuel Blog

Find the latest Refuel news, research, demos, and engineering updates here.

Research
Labeling with Confidence

In this post we examine different techniques for estimating confidence of LLM generated labels, and demonstrate how to leverage these to automatically reject low confidence labels and ensemble LLMs optimally

Read More
gpt-3.5-turbo-0613 is worse than gpt-3.5-turbo-0301
Research
Is the new gpt-3.5-turbo model worse?

In this report, we compare the latest models from OpenAI against their previous versions on a data labeling benchmark to find that gpt-3.5-turbo is worse for 6/8 datasets, while gpt-4 performance remains the same.

Read More
Evaluation of LLMs across labeling tasks
Research
LLMs can label data as well as humans, but 100x faster

In this report, we show that LLMs can label datasets 20x faster, and 7x cheaper, but at the same or better quality compared to skilled human annotators.

Read More
Refuel logo
Company
Refuel: Accelerating the era of AI abundance

We are entering the era of AI abundance. Foundation models' broad capabilities to understand language and vision is a huge unlock for building AI applications across every vertical - from healthcare to education to supply chains. 

Read More
The Autolabel product logo
Open-source
Autolabel: Open-source library to label all your NLP datasets

Today, we’re excited to announce Autolabel, an open-source Python library to label NLP datasets with any LLM of your choice. 

Read More
About UsCareersBlogDocs

© 2023 Refuel.ai, Inc.
‍
Privacy Policy     
Terms of Service
Get updates from Refuel
Thank you! You'll hear from us soon.
Oops! Something went wrong. Please try again.