World Congress 2024 • Aug 22, 2024 • Session details

Give Your LLMs a Left Brain

Are hallucinations stalling your production apps? Learn how integrating knowledge graphs builds a deterministic left brain for your LLMs, ensuring secure, traceable, and logical enterprise outputs.

Pause

Mute

Enter Fullscreen

#1 about 4 min

Challenges of adopting LLMs for enterprise applications

Commercial LLMs trained on broad datasets face significant obstacles when applied to specific enterprise contexts and problems.

#2 about 7 min

Demonstrating LLM hallucinations with math and reasoning

Examples reveal how mixing math, reasoning, and biases causes commercial models to generate illogical or hallucinatory responses.

#3 about 5 min

How LLMs process language using word vectors

Large language models leverage transformers and multi-dimensional word vectors to statistically predict information rather than applying structured logic.

#4 about 5 min

Combining knowledge graphs with LLMs for reliability

Integrating knowledge graphs provides explicit domain understanding and deterministic answers that pure vector databases and language models lack.

#5 about 3 min

Comparing vector search to graph-enhanced retrieval approaches

A side-by-side analysis demonstrates how adding graph context transforms generic responses into actionable and heavily detailed business insights.

#6 about 2 min

Architecting a hybrid vector and knowledge graph system

Routing user queries through both knowledge graphs and vector databases enables context enrichment and continuous algorithmic fine-tuning.

#7 about 3 min

Improving data governance and auditability with graphs

Modeling organizational data as graph nodes ensures strict access controls, response explainability, and full audit traceability for production environments.

#8 about 3 min

Educational resources for building graph-backed AI applications

Developers can leverage specialized courses and tutorials to implement graph retrieval using frameworks like LangChain and Python.

Matching moments

6:03 min

Architecting a semantic long-term memory system for LLMs

Erik Bamberg · LIVE

1:35 min

How LLMs imitate human data discovery behavior

Jordan Tigani

Jordan Tigani · World Congress 2026 Europe

1:59 min

Building culturally aware LLMs for global audiences

Werner Vogels

Werner Vogels +1 · World Congress 2026 Europe

1:44 min

Introduction to generative AI and knowledge graphs

Michael Hunger

Michael Hunger · World Congress 2024

3:26 min

Introducing LLMs as judges for automated testing

Sebastian Messingfeld

Sebastian Messingfeld · World Congress 2026 Europe

2:05 min

Enhancing language models with retrieval-augmented generation

Mary Grygleski

Mary Grygleski · LIVE

More from World Congress 2024

Beyond the Hype: Real-World AI Strategies Panel thumbnail

Beyond the Hype: Real-World AI Strategies Panel

Mike Butcher, Jürgen Müller, Katrin Lehmann, Tobias Regenfuss

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation thumbnail

almost 2 years ago

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI! thumbnail

about 2 years ago

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI!

Zaid Zaim

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging thumbnail

about 2 years ago

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging

Sue Quackenbush

Dapr in Practice thumbnail

about 2 years ago

Dapr in Practice

marcklefter

Minimising the Carbon Footprint of Workloads thumbnail

about 2 years ago

Minimising the Carbon Footprint of Workloads

Michael Mueller

Upcoming sessions on this topic

World Congress 2026 North America

September 24, 2026 · 13:30–14:00

Stage 9

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Director - AI & Governance at Humanity + AI, Inc

Jofia Jose Prakash

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 6

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong

World Congress 2026 North America

September 24, 2026 · 16:10–16:40

Stage 9

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

Legare Kerrison, Cedric Clyburn

Legare Kerrison

Cedric Clyburn

World Congress 2026 North America

September 25, 2026 · 09:40–10:10

Stage 7

Loop Engineering

Li Yin

CEO

Li Yin

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 9

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan

World Congress 2026 North America

September 25, 2026 · 14:10–14:40

Stage 4

Headroom: A Context Optimization Layer for LLM Applications

Tejas Chopra

Senior Software Engineer at Netflix

Tejas Chopra

Related videos

Large Language Models ❤️ Knowledge Graphs thumbnail

World Congress 2024 • about 2 years ago

Large Language Models ❤️ Knowledge Graphs

Michael Hunger

Martin O'Hanlon - Make LLMs make sense with GraphRAG thumbnail

LIVE • over 1 year ago

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Martin O'hanlon

Knowledge graph based chatbot thumbnail

World Congress 2023 • almost 3 years ago

Knowledge graph based chatbot

Tomaz Bratanic

Lies, Damned Lies and Large Language Models thumbnail

LIVE • almost 2 years ago

Lies, Damned Lies and Large Language Models

Jodie Burchell

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge thumbnail

Coffee With Developers • over 1 year ago

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel, Guillaume Laforge

Scaling GraphRAG: Efficient Knowledge Retrieval for AI thumbnail

World Congress 2026 Europe • 2 months ago

Scaling GraphRAG: Efficient Knowledge Retrieval for AI

Gal Shubeli

Related articles

LM

Luis Minvielle

What Are Large Language Models?

Developers and writers can finally agree on one thing: Large Language Models, the subset of AIs that drive ChatGPT and its competitors, are stunning tech creations. Developers enjoying the likes of...

almost 3 years ago

What Are Large Language Models?

MH

Michael Hunger

N

Neo4j

Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?

After a few intense years of building with AI, many teams are asking the same question: Where is the ROI? We’re shipping chatbots, copilots, and agents . But: Agents aren’t autonomous enough to ow...

8 months ago

An abstract image of nodes representing a graph database

DC

Daniel Cranney

ChatGPT on AI Hallucinations: Can It Fix Its Own Mistakes?

Most of us use AI daily—whether summarizing text, organizing tasks, suggesting recipes, or even translating languages in real time. As AI chatbots become more integrated into our lives, we increasi...

over 1 year ago

A ChatGPT-style interface with the prompt 'Please give me some advice about how to handle AI hallucinations'

BR

Benjamin Ruschin

Who Owns Your Content in the Age of LLMs?

AI has changed the web forever. Large language models (LLMs) are changing how information is produced, shared and consumed on the web. In fact, estimates suggest that now more than half of all web ...

about 1 year ago

A person finding bots

From learning to earning

Jobs that call for the skills explored in this talk.

19 days ago • Verified

Partner Sales Director - AI Alliances - Model Providers

San Francisco, United States

Expert Remote DevOps AI Frameworks Machine Learning

24 days ago • Verified

LLM Dataset Engineer

San Francisco, United States

Expert $155k–210k Python

24 days ago • Verified

LLM Training Engineer

San Francisco, United States

Expert $155k–220k Python

26 days ago • Verified

Senior AI/ML Engineer

Lisbon, Portugal

Expert Remote AI Frameworks AI-assisted coding tools

Machine Learning Engineer

Experienced Remote Spacy Pytorch Chatbots

14 days ago • Verified

ML Engineer

Seattle, United States

Expert Remote Go