Scribd Logo
Upload

Welcome to Scribd!

  • 292 views

    Large Language Models: CSC413 Tutorial 9 Yongchao Zhou

    Uploaded by

    sidh.singh73
    The document discusses large language models (LLMs), including what they are, why they are useful, how they are trained, and some of their emergent capabilities and risks. LLMs have billions of parameters and are trained on massive datasets using self-supervised objectives. During training, they learn general language representations that allow them to perform many NLP tasks without extensive fine-tuning. Emergent capabilities include in-context learning, advanced prompting techniques, and zero-shot chains of thought. Risks include potential for harm from mistakes, misuse, biases, and attacks.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Large Language Models: CSC413 Tutorial 9 Yongchao Zhou

    Uploaded by

    sidh.singh73
    292 views40 pages
    The document discusses large language models (LLMs), including what they are, why they are useful, how they are trained, and some of their emergent capabilities and risks. LLMs have billions of parameters and are trained on massive datasets using self-supervised objectives. During training, they learn general language representations that allow them to perform many NLP tasks without extensive fine-tuning. Emergent capabilities include in-context learning, advanced prompting techniques, and zero-shot chains of thought. Risks include potential for harm from mistakes, misuse, biases, and attacks.

    Original Title

    llm-ppt

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses large language models (LLMs), including what they are, why they are useful, how they are trained, and some of their emergent capabilities and risks. LLMs have billions of parameters and are trained on massive datasets using self-supervised objectives. During training, they learn general language representations that allow them to perform many NLP tasks without extensive fine-tuning. Emergent capabilities include in-context learning, advanced prompting techniques, and zero-shot chains of thought. Risks include potential for harm from mistakes, misuse, biases, and attacks.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    292 views40 pages

    Large Language Models: CSC413 Tutorial 9 Yongchao Zhou

    Uploaded by

    sidh.singh73
    The document discusses large language models (LLMs), including what they are, why they are useful, how they are trained, and some of their emergent capabilities and risks. LLMs have billions of parameters and are trained on massive datasets using self-supervised objectives. During training, they learn general language representations that allow them to perform many NLP tasks without extensive fine-tuning. Emergent capabilities include in-context learning, advanced prompting techniques, and zero-shot chains of thought. Risks include potential for harm from mistakes, misuse, biases, and attacks.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 40

    Large Language Models

    CSC413 Tutorial 9
    Yongchao Zhou
    Overview
    ● What are LLMs?
    ● Why LLMs?
    ● Emergent Capabilities
    ○ Few-shot In-context Learning
    ○ Advanced Prompt Techniques
    ● LLM Training
    ○ Architectures
    ○ Objectives
    ● LLM Finetuning
    ○ Instruction finetuning
    ○ RLHF
    ○ Bootstrapping
    ● LLM Risks
    What are Language Models?
    ● Narrow Sense
    ○ A probabilistic model that assigns a probability to every finite sequence (grammatical or not)

    ● Broad Sense
    ○ Decoder-only models (GPT-X, OPT, LLaMA, PaLM)
    ○ Encoder-only models (BERT, RoBERTa, ELECTRA)
    ○ Encoder-decoder models (T5, BART)
    Large Language Models - Billions of Parameters

    https://huggingface.co/blog/large-language-models
    Large Language Models - Hundreds of Billions of Tokens

    https://babylm.github.io/
    Large Language Models - yottaFlops of Compute

    https://web.stanford.edu/class/cs224n/slides/cs224n-2023-lecture11-prompting-rlhf.pdf
    Why LLMs?
    ● Scaling Law for Neural Language Models
    ○ Performance depends strongly on scale! We keep getting better performance as we scale
    the model, data, and compute up!

    https://arxiv.org/pdf/2001.08361.pdf
    Why LLMs?
    ● Generalization
    ○ We can now use one single model to solve many NLP tasks

    https://arxiv.org/pdf/1910.10683.pdf
    Why LLMs?
    ● Emergent Abilities
    ○ Some ability of LM is not present in smaller models but is present in larger models

    https://docs.google.com/presentation/d/1yzbmYB5E7G8lY2-KzhmArmPYwwl7o7CUST1xRZDUu1Y/edit?resourcekey=0-6_TnUMoK
    WCk_FN2BiPxmbw#slide=id.g1fc34b3ac18_0_27
    Emergent Capability - In-Context Learning

    https://arxiv.org/pdf/2005.14165.pdf
    Emergent Capability - In-Context Learning

    https://www.cs.princeton.edu/courses/archive/fall22/cos597G/lectures/lec04.pdf
    Emergent Capability - In-Context Learning
    Pretraining + Fine-tuning Paradigm
    Pretraining + Prompting Paradigm
    ● Fine-tuning (FT) Stronger
    ○ + Strongest performance task-specific
    ○ - Need curated and labeled dataset for each performance
    new task (typically 1k-100k ex.)
    ○ - Poor generalization, spurious feature
    exploitation
    ● Few-shot (FS)
    ○ + Much less task-specific data needed
    ○ + No spurious feature exploitation
    ○ - Challenging
    ● One-shot (1S)
    ○ + "Most natural," e.g. giving humans instructions
    ○ - Challenging
    ● Zero-shot (OS)
    ○ + Most convenient More convenient,
    ○ - Challenging, can be ambiguous
    general, less data
    Emergent Capability - Chain of Thoughts Prompting

    https://arxiv.org/pdf/2201.11903.pdf
    Emergent Capability - Chain of Thoughts Prompting

    https://arxiv.org/pdf/2201.11903.pdf
    Emergent Capability - Zero Shot CoT Prompting

    https://arxiv.org/pdf/2205.11916.pdf
    Emergent Capability - Zero Shot CoT Prompting

    https://arxiv.org/pdf/2205.11916.pdf
    Emergent Capability - Self-Consistency Prompting

    https://arxiv.org/pdf/2203.11171.pdf
    Emergent Capability - Least-to-Most Prompting

    https://arxiv.org/pdf/2205.10625.pdf
    Emergent Capability - Augmented Prompting Abilities

    Advanced Prompting Techniques Ask a human to

    ● Zero-shot CoT Prompting ● Explain the rationale


    ● Self-Consistency ● Double check the answer
    ● Divide-and-Conquer ● Decompose to easy subproblems

    Large Language Models demonstrate some human-like behaviors!


    Training Architectures

    Encoder-decoder models (T5, BART) Decoder-only models (GPT-X, PaLM)

    http://jalammar.github.io/illustrated-transformer/
    Training Objectives - UL2

    https://arxiv.org/pdf/2205.05131.pdf
    What kinds of things does pretraining learn?

    https://web.stanford.edu/class/cs224n/slides/cs224n-2023-lecture11-prompting-rlhf.pdf
    Finetune - Instruction Finetune

    https://arxiv.org/pdf/2210.11416.pdf
    Finetune - Instruction Finetune

    https://arxiv.org/pdf/2210.11416.pdf
    Finetune - Instruction Finetune

    https://arxiv.org/pdf/2210.11416.pdf
    Finetune - Instruction Finetune

    https://arxiv.org/pdf/2210.11416.pdf
    Finetune - RLHF

    https://arxiv.org/pdf/2203.14465.pdf
    Application - ChatGPT
    Application - ChatGPT

    https://yaofu.notion.site/How-does-GPT-Obtain-its-Ability-Tracing-Emergent-Abilities-of-Language-Models-to-their-Source
    s-b9a57ac0fcf74f30a1ab9e3e36fa1dc1
    Finetune - Bootstrapping

    https://arxiv.org/pdf/2203.14465.pdf
    Finetune - Bootstrapping

    https://arxiv.org/pdf/2210.11610.pdf
    Large Language models Risks
    ● LLMs make mistakes

    (falsehoods, hallucinations)

    ● LLMs can be misused

    (misinformation, spam)

    ● LLMs can cause harms

    (toxicity, biases, stereotypes)

    ● LLMs can be attacked

    (adversarial examples, poisoning, prompt injection)

    ● LLMs can be useful as defenses

    (content moderation, explanations)


    Resources for further reading
    ● https://web.stanford.edu/class/cs224n/
    ● https://stanford-cs324.github.io/winter2022/
    ● https://stanford-cs324.github.io/winter2023/
    ● https://www.cs.princeton.edu/courses/archive/fall22/cos597G/
    ● https://rycolab.io/classes/llm-s23/
    ● https://yaofu.notion.site/How-does-GPT-Obtain-its-Ability-Tracing-Emergent-Ab
    ilities-of-Language-Models-to-their-Sources-b9a57ac0fcf74f30a1ab9e3e36fa1d
    c1
    ● https://www.jasonwei.net/blog/emergence
    Emergent Capability - In-Context Learning

    https://arxiv.org/pdf/2005.14165.pdf
    Emergent Capability - Decomposed Prompting

    https://arxiv.org/pdf/2210.02406.pdf
    Training Objectives - UL2

    https://arxiv.org/pdf/2205.05131.pdf
    Training Techniques - Parallelism

    https://openai.com/research/techniques-for-training-large-neural-networks
    Training Techniques - Parallelism

    https://www.microsoft.com/en-us/research/blog/deepspeed-extreme-scale-model-training-for-everyone/

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy