WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Outclassing Frontier LLMs at Extracting Information

Etienne Bernard

A specialized 4B model reduced complex document extraction errors from 70% to just 3%. Discover how NuExtract3 outclasses massive frontier LLMs directly on a single GPU.

Starting at 24:05 · Watch from the beginning

Outclassing Frontier LLMs at Extracting Information thumbnail

Checking access…

Playback and chapters load privately for Free videos.

Matching moments

6:43 min

Replacing LLMs with specialized data extractors

Dmytro Kurets Dmytro Kurets · Europe 2026 Virtual

2:47 min

Building cost-effective entity extraction pipelines for unstructured data

William Lyon · Coffee With Developers

4:39 min

Enhancing legacy record extraction using machine learning

Maria Doina Irimias · LIVE

1:26 min

The naive document extraction pipeline architecture

Nazeer Saeed Nazeer Saeed · World Congress 2026 Europe

1:45 min

Evaluating document extraction performance with benchmarking tools

Luca Bianchi Luca Bianchi · World Congress 2026 Europe

3:13 min

Processing unstructured data through intelligent document understanding

Boris Krumrey +2 · LIVE

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan +1

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann · WeAreDevelopers

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen · NetApp

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic · adjoe

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray · Stack8s

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert +1

Upcoming sessions on this topic

Open session

Decision models for developers who use LLMs

  • Anurag Bhandari

    antelligent

    CTO

Open session

Enterprise AI Memory at Scale

  • Aditya Joshi

    Walmart

    Senior Software Engineer

Open session

Bypassing the GPU Tax: Smart Layer-7 Routing with Small Language Models (SLMs)

  • Sagar Utekar

    CrowdStrike

    SRE

Open session

Engineering AI Strategy: Beyond the Hype

  • Omkar Srivastava

    ADSK

    Engineering Leader

Open session

The Dream Team You Didn't Know You Had - Multi-Model, Multi-Agent, One Software Lifecycle

  • Aditya Dua

    GitHub

    Senior Manager, Field Services, SAARC

Open session

Built-In AI in the Browser: Practical Capabilities for Modern Web Apps

  • Piyush Gupta

    Expedia

    Senior Engineering Manager

Related videos

Garbage In, Garbage Out: Engineering Reliable AI Document Extraction Pipelines thumbnail
27:24

Garbage In, Garbage Out: Engineering Reliable AI Document Extraction Pipelines

Nazeer Saeed · Apryse

World Congress Europe · 2026

Event-Driven AI Agents: Orchestrating Long-Context Legal Processing at Scale thumbnail
32:26

Event-Driven AI Agents: Orchestrating Long-Context Legal Processing at Scale

Luca Bianchi · MESA

World Congress Europe · 2026

AI That Fits Your Business, Not the Other Way Around thumbnail
25:56

AI That Fits Your Business, Not the Other Way Around

Anshul Jindal +1

World Congress Europe · 2026

Inside the Mind of an LLM thumbnail
27:11

Inside the Mind of an LLM

Emanuele Fabbiani · xtream

World Congress · 2025

Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source thumbnail
29:50

Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source

Viktoria Semaan · databricks

World Congress Europe · 2026

Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization thumbnail
26:27

Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization

Legare Kerrison +1

World Congress North America · 2026

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.