Blog

Articles

NuExtract 1.5 - Multilingual, Infinite context, still small, and better than GPT-4o!
Research

NuExtract 1.5 - Multilingual, Infinite context, still small, and better than GPT-4o!

We introduce NuExtract 1.5, the new version of our foundation model for structured extraction. NuExtract 1.5 is multilingual, can handle arbitrarily long documents, and outperforms GPT-4o in English while being 500 times smaller. As usual, we release it under MIT license.

October 14, 2024

Latest posts

All
Research
All
Resources
All
Updates
Research

NuExtract 1.5 - Multilingual, Infinite context, still small, and better than GPT-4o!

We introduce NuExtract 1.5, the new version of our foundation model for structured extraction. NuExtract 1.5 is multilingual, can handle arbitrarily long documents, and outperforms GPT-4o in English while being 500 times smaller. As usual, we release it under MIT license.

October 14, 2024
NuExtract 1.5 - Multilingual, Infinite context, still small, and better than GPT-4o!
Updates

NuMind is Out!

NuMind is a tool to create custom NLP models by “teaching” an AI. It can be used to create high-quality lightweight information extraction models without sharing your data with anyone. Under the hood, NuMind uses in-house foundation models, automatic machine learning, and an active learning strategy to get high-performance without spending too much time correcting the model.

August 5, 2024
NuMind is Out!
Research

NuExtract: A Foundation Model for Structured Extraction

We introduce NuExtract, a lightweight text-to-JSON LLM. NuExtract allows to extract arbitrarily complex information from text and turns it into structured data. This model can be directly used in a zero-shot setting or fine-tuned to solve a specific extraction problem. As usual, we open-source it under MIT license for everyone to use.

June 24, 2024
NuExtract: A Foundation Model for Structured Extraction
Research

A Foundation Model for Entity Recognition

Entity recognition is a widely used information extraction task, yet publicly available foundation models are not well suited for it. We leverage modern LLMs to create a small-yet-powerful foundation model for this task. This BERT-size model can be used to create custom entity recognizers with typically 5x less annotated data than before. This model is powering NuMind and we open-source it with an MIT license for everyone to use. Spread the word!

November 7, 2023
A Foundation Model for Entity Recognition
Research

Creating Task-Specific Foundation Models with GPT-4

There are two kinds of BERT-size NLP models in this world: general-purpose ones (a.k.a. foundation models), and highly specialized ones, trained on specific tasks and data. Neither kind is ideal to solve particular NLP problems on your data. We need to fill this specialization gap with task-specific foundation models, and propose a way to create them efficiently using LLMs. We apply this method to create a state-of-the-art domain-agnostic foundation model for Sentiment Analysis that we open source for everyone to use.

August 25, 2023
Creating Task-Specific Foundation Models with GPT-4
Resources

What are Large Language Models?

These past few months, thanks to ChatGPT and its siblings, we have been witnessing something historic. It seems that computers are finally able to understand our language, and are even able to speak back! These AIs are the latest iterations of large language models, also known as LLMs. But what exactly are these LLMs? How do they work? And how are they created? Let's dive into it.

June 21, 2023
What are Large Language Models?
Updates

Seed Round Completed

We are delighted to announce that we closed a seed funding round! We raised $3M, which we will use to continue building our NLP tool focused on text understanding.

March 30, 2023
Seed Round Completed