Large
Languag
e
Models
Agenda
Introduction
Why LLM’s?
About LLM (Large Language Models)
NLP (Natural Language Models)
LL (Language Models)
Introduction
Why
LLMs?
1.Versatility: They can perform a wide range of natural language processing tasks, such as text
generation, translation, summarization, sentiment analysis, and more, due to their large-scale training
on diverse textual data.
2.Contextual Understanding: LLMs excel at understanding context within text, enabling them to
generate responses that are contextually relevant and coherent, leading to more human-like
interactions.
3.Scalability: With their massive size and parallel processing capabilities, LLMs can handle large
volumes of data efficiently, making them suitable for handling complex language tasks at scale.
4.Continuous Learning: LLMs can be fine-tuned on specific datasets or domains, allowing them to
adapt and improve their performance over time, making them adaptable to various use cases and
scenarios.
Questions we
hear about
LLMs
Is the LLM How to
hype real? Is Are LLMs a leverage LLMs How to
this an threat or an to gain a quickly apply
iPhone opportunity? competitive LLMs to my
moment? advantage? data?
LLMs are more than
hype
They are revolutionizing every industry
“Chegg shares drop more than 4O% “[...] ask GitHub Copilot to explain a
after company says ChatGPT is killing piece of code. Bump into an
its business” error? Have GitHub Copilot fix it.
It’ll even generate unit tests so
you can get back to building
05/02/2023 what’s next.”
Link
03/22/2023*
Link
“[YouChat is an] AI search assistant
that you can talk to right in your
search results. It stays up-to-date
with the news and cites its sources
so that you can feel confident in
its answers.”
12/23/2022
Link
LLMs are not that
new
Why should I care now?
Accuracy and effectiveness has
hit a tipping point
• Many new use cases are unlocked!
• Accessible by all.
Readily available data and tooling
• Large datasets.
• Open-sourced model options.
• Requires powerful GPUs, but are available
on the cloud.
What is an LLM?
It’s a large language model trained on enormous
data
What does that?
LLMs automate many human-led tasks
Choose the right LLM
There is no “perfect” model. Trade-offs are
required.
Decision criteria
Model Quality Serving Cost Serving Customizability
Latency
Primer on NLP
Natural Language Processing
What is NLP?
We use NLP
everyday
NLP is useful for a variety of
domains
Sentiment analysis: product reviews Other use
This book was terrible and went
on and on about…
Negative cases
• Literaturesimilarity
Semantic search.
• Database querying.
Translatio • Question-Answer matching.
n Summarization
Me gusta este libro.
• Clinical decision support.
I like this book. • News article sentiments.
• Legal proceeding summary.
Question answering: chatbots
Text
It really depends on your classification
• Customer review sentiments.
What’s the best scifi book ever? preferences. Some of the •
top-rated ones include…
Genre/topic classification.
Some useful NLP
definitions
The moon, Earth's only natural satellite, has been a subject of fascination and wonder for thousands of
years.
Token Sequence Vocabulary
Basic building block Sequential list of tokens Complete list of tokens
• The • The moon, {
• Moon • Earth’s only natural satellite
1:"The",
• , • Has been a subject of
• Earth’s • …. 569:"moon",
• Only • Thousands of years
122: ",",
• …..
• years 430:"Earth",
50:"**’s",
…}
Types of sequence
tasks
Translation
I like this book. Me gusta este Sequence to sequence
libro. prediction
Sequence of text
Sequence of text
Sentiment analysis
This book was terrible and went(product reviews)
Negative Sequence to non sequence
on and on about… prediction
Sequence of text Label
Question answering (chatbots)
It really depends on your Sequence to sequence
What’s the best scifi book ever? preferences. Some of the generation
top-rated ones include…
Sequence of
text Sequence of text
NLP goes beyond
text
Speech recognition
Image caption generation
Image generation from text
Text interpretation is
challenging
“The ball hit the table and it broke.” “What’s the best sci-fi book ever?”
Context can There can be
Language is
change the multiple good
meaning. answers.
ambiguous.
Input data format matters.
Lots of work has gone into text representation for NLP.
Model size matters.
Big models help to capture the diversity and complexity of human language.
Training data matters.
It helps to have high-quality data and lots of it.
Language Models:
How to predict and analyze
text
What is a Language
Model?
The term Large Language Models is everywhere these days.
But let’s take a closer look at that term:
Large Language Model—What is a Language Model?
Large Language Model—What about these makes them “larger” than other language models?
What is a Language Model?
LMs assign probabilities to word sequences: find the most likely
word
Categories:
• Generative: find the most likely next word
• Classification: find the most likely classification/answer
What is a Large Language
Model?
Language Model Description “Large”? Emergence
Represents text as a set of unordered words, without
Bag-of-Words Model No 195Os-196Os
considering sequence or context
Considers groups of N consecutive words to capture
N-gram Model No 195Os-196Os
sequence
Hidden Markov Models Represents language as a sequence of hidden states
No 198Os-199Os
(HMMs) and observable outputs
Recurrent Neural Networks Processes sequential data by maintaining an internal
No 199Os-2O1Os
(RNNs) state, capturing context of previous inputs
Long Short-Term Memory Extension of RNNs that captures longer-term
No 2O1Os
(LSTM) Networks dependencies
Neural network architecture that processes sequences
Transformers of variable length using a self-attention mechanism
Yes 2017-Present
Natural Language Processing
(NLP)
Let’s review
• NLP is a field of methods to process text.
• NLP is useful: summarization, translation, classification, etc.
• Language models (LMs) predict words by looking at word probabilities.
• Large LMs are just LMs with transformer architectures, but bigger.
• Tokens are the smallest building blocks to convert text to numerical
vectors, aka N-dimensional embeddings.
Thank you
