Refuel Blog

Analyzing Call Transcripts with LLMs

A guide to leveraging Refuel to extract insights from call and conversational transcripts

Finding the right SLM for your needs - a guide to Small Language Models

A guide to improving marketplace search, data quality, and onboarding with LLMs

LLMs can have a transformative impact in scaling key marketplace workflows by automating key aspects of the workflows. LLMs can streamline supplier verification, detect fraud during the onboarding process, facilitate high-fidelity product tagging and perform automated content review

How to score and qualify leads with LLMs

Lead scoring and qualification can be challenging with a manual approach. We built an LLM based solution to automatically qualify and score inbound leads based on defined rules and historical data.

Parsing and extracting from resumes with LLMs

Resumes are tricky to parse and extract from due to challenges in format and terminology inconsistencies. This post outlines a multi-step approach to parsing and extracting resumes in bulk, with LLMs and AI.

Announcing Refuel LLM-2

Refuel is SOC2 Compliant

Refuel announces the successful completion of their SOC 2 Type I audit, underscoring their ongoing commitment to data security and privacy as a cornerstone of customer trust and satisfaction.

TeachFX: Refuel helps TeachFX ship AI features in 2 weeks instead of 2 months

TeachFX, an ed-tech company, partnered with Refuel to generate accurate training datasets, achieving over 92% agreement with expert annotators, and reduced the time for new AI feature development from months to just two weeks.

Beni: Refuel helps Beni improve accuracy from 46% to 87% on product catalog of 200M+ items, driving partner revenue increase

In the highly competitive $245B resale market, Beni, a secondhand shopping tool, partnered with Refuel to tackle its data normalization challenge across a 200M+ item catalog.

Refuel Cloud: End to end platform for solving enterprise data tasks with LLMs, integrated in your environment

Announcing Refuel-LLM

Announcing the launch of Refuel LLM, a large language model purpose built for data labeling and enrichment tasks. 

Improving data quality 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

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.

LLMs can structure 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.

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. 

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.