Emanuele Fabbiani

Inside the Mind of an LLM

An LLM leaking private data isn't a bug, it's a core feature. Learn why deep learning models are fundamentally designed to memorize unique information.

Inside the Mind of an LLM
#1about 7 minutes

Understanding the risks of large language models

LLMs are often used without understanding their inner workings, leading to factual errors and the generation of insecure code.

#2about 8 minutes

How large language models are trained

A four-phase process explains how models learn language through pre-training, are taught tasks, aligned with human preferences, and refined using reinforcement learning.

#3about 5 minutes

Why Llama 2 models think in English

Research on Llama 2 models reveals they use English as an internal representation for all tasks due to its prevalence in the training data.

#4about 4 minutes

Controlling LLM behavior with monosemantic features

By identifying and amplifying single-meaning concepts, or monosemantic features, it is possible to deterministically control a model's output on specific topics.

#5about 2 minutes

Why LLMs memorize and leak private data

Deep learning models inherently memorize unique outlier data from their training set, which explains why LLMs can leak personal information and pose a privacy risk.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Videos

Three years of putting LLMs into Software - Lessons learned26:30

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Adding knowledge to open-source LLMs25:35

Adding knowledge to open-source LLMs

Sergio Perez, Harshita Seth

Self-Hosted LLMs: From Zero to Inference30:04

Self-Hosted LLMs: From Zero to Inference

Roberto Carratalá, Cedric Clyburn

Data Privacy in LLMs: Challenges and Best Practices23:50

Data Privacy in LLMs: Challenges and Best Practices

Aditi Godbole

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails29:00

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

Unlocking the Power of AI: Accessible Language Model Tuning for All31:50

Unlocking the Power of AI: Accessible Language Model Tuning for All

Cedric Clyburn, Legare Kerrison

Exploring LLMs across clouds28:38

Exploring LLMs across clouds

Tomislav Tipurić

Using LLMs in your Product31:12

Using LLMs in your Product

Daniel Töws

From learning to earning

Jobs that call for the skills explored in this talk.