> Markdown version of [/@etienne-bernard](https://www.wearedevelopers.com/@etienne-bernard). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Etienne Bernard
Building specialized, low-hallucination language models for information extraction.

## About

Etienne Bernard builds specialized language models for information extraction at NuMind. He focuses on solving the hallucination and layout issues that cause generic models to struggle with complex documents.

Before founding NuMind, he led the machine learning team at Wolfram Research and wrote *Introduction to Machine Learning*. Today, his work centers on open-source tools like NuExtract and NuMarkdown, proving that smaller, targeted models can outperform giants like GPT-5 in specific extraction tasks.

He holds a PhD in physics from ENS and MIT.



## Past Sessions

### World Congress 2026 Europe · July 8, 2026
Berlin, Germany
- [Outclassing Frontier LLMs at Extracting Information](https://www.wearedevelopers.com/videos/100303-outclassing-frontier-llms-at-extracting-information) · 30 min · 🎥 Watch recording



## Videos

- [Outclassing Frontier LLMs at Extracting Information](https://www.wearedevelopers.com/videos/100303-outclassing-frontier-llms-at-extracting-information) · Etienne Bernard


## Links

- [X](https://x.com/etiennebcp?lang=en)
- [LinkedIn](https://www.linkedin.com/in/etiennebcp/)
- [Blog](https://numind.ai/blog/what-are-large-language-models)