A non-technical overview of Large Language Models, exploring their potential, limitations, and customization for specific challenges. While this deck is tailored for an audience from the financial industry in mind, its content remains broadly applicable.
(This updated version builds on our previous deck: slideshare.net/LoicMerckel/intro-to-llms.)
A non-technical overview of Large Language Models, exploring their potential, limitations, and customization for specific challenges. While this deck is tailored for an audience from the financial industry in mind, its content remains broadly applicable.
(Note: Discover a slightly updated version of this deck at slideshare.net/LoicMerckel/introduction-to-llms.)
* "Responsible AI Leadership: A Global Summit on Generative AI"
*April 2023 guide for experts and policymakers
* Developing and governing generative AI systems
* + 100 thought leaders and practitioners participated
* Recommendations for responsible development, open innovation & social progress
* 30 action-oriented recommendations aim
* Navigate AI complexities
Generative AI: Past, Present, and Future – A Practitioner's PerspectiveHuahai Yang
Generative AI: Past, Present, and Future – A Practitioner's Perspective
As the academic realm grapples with the profound implications of generative AI
and related applications like ChatGPT, I will present a grounded view from my
experience as a practitioner. Starting with the origins of neural networks in
the fields of logic, psychology, and computer science, I trace its history and
align it within the wider context of the pursuit of artificial intelligence.
This perspective will also draw parallels with historical developments in
psychology. Against this backdrop, I chart a proposed trajectory for the future.
Finally, I provide actionable insights for both academics and enterprising
individuals in the field.
A non-technical overview of Large Language Models, exploring their potential, limitations, and customization for specific challenges. While this deck is tailored for an audience from the financial industry in mind, its content remains broadly applicable.
(Note: Discover a slightly updated version of this deck at slideshare.net/LoicMerckel/introduction-to-llms.)
* "Responsible AI Leadership: A Global Summit on Generative AI"
*April 2023 guide for experts and policymakers
* Developing and governing generative AI systems
* + 100 thought leaders and practitioners participated
* Recommendations for responsible development, open innovation & social progress
* 30 action-oriented recommendations aim
* Navigate AI complexities
Generative AI: Past, Present, and Future – A Practitioner's PerspectiveHuahai Yang
Generative AI: Past, Present, and Future – A Practitioner's Perspective
As the academic realm grapples with the profound implications of generative AI
and related applications like ChatGPT, I will present a grounded view from my
experience as a practitioner. Starting with the origins of neural networks in
the fields of logic, psychology, and computer science, I trace its history and
align it within the wider context of the pursuit of artificial intelligence.
This perspective will also draw parallels with historical developments in
psychology. Against this backdrop, I chart a proposed trajectory for the future.
Finally, I provide actionable insights for both academics and enterprising
individuals in the field.
And then there were ... Large Language ModelsLeon Dohmen
It is not often even in the ICT world that one witnesses a revolution. The rise of the Personal Computer, the rise of mobile telephony and, of course, the rise of the Internet are some of those revolutions. So what is ChatGPT really? Is ChatGPT also such a revolution? And like any revolution, does ChatGPT have its winners and losers? And who are they? How do we ensure that ChatGPT contributes to a positive impulse for "Smart Humanity?".
During a key note om April 3 and 13 2023 Piek Vossen explained the impact of Large Language Models like ChatGPT.
Prof. PhD. Piek Th.J.M. Vossen, is Full professor of Computational Lexicology at the Faculty of Humanities, Department of Language, Literature and Communication (LCC) at VU Amsterdam:
What is ChatGPT? What technology and thought processes underlie it? What are its consequences? What choices are being made? In the presentation, Piek will elaborate on the basic principles behind Large Language Models and how they are used as a basis for Deep Learning in which they are fine-tuned for specific tasks. He will also discuss a specific variant GPT that underlies ChatGPT. It covers what ChatGPT can and cannot do, what it is good for and what the risks are.
An Introduction to Generative AI - May 18, 2023CoriFaklaris1
For this plenary talk at the Charlotte AI Institute for Smarter Learning, Dr. Cori Faklaris introduces her fellow college educators to the exciting world of generative AI tools. She gives a high-level overview of the generative AI landscape and how these tools use machine learning algorithms to generate creative content such as music, art, and text. She then shares some examples of generative AI tools and demonstrate how she has used some of these tools to enhance teaching and learning in the classroom and to boost her productivity in other areas of academic life.
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...David Talby
An April 2023 presentation to the AMIA working group on natural language processing. The talk focuses on three current trends in NLP and how they apply in healthcare: Large language models, No-code, and Responsible AI.
This talk overviews my background as a female data scientist, introduces many types of generative AI, discusses potential use cases, highlights the need for representation in generative AI, and showcases a few tools that currently exist.
The Future of AI is Generative not Discriminative 5/26/2021Steve Omohundro
The deep learning AI revolution has been sweeping the world for a decade now. Deep neural nets are routinely used for tasks like translation, fraud detection, and image classification. PwC estimates that they will create $15.7 trillion/year of value by 2030. But most current networks are "discriminative" in that they directly map inputs to predictions. This type of model requires lots of training examples, doesn't generalize well outside of its training set, creates inscrutable representations, is subject to adversarial examples, and makes knowledge transfer difficult. People, in contrast, can learn from just a few examples, generalize far beyond their experience, and can easily transfer and reuse knowledge. In recent years, new kinds of "generative" AI models have begun to exhibit these desirable human characteristics. They represent the causal generative processes by which the data is created and can be compositional, compact, and directly interpretable. Generative AI systems that assist people can model their needs and desires and interact with empathy. Their adaptability to changing circumstances will likely be required by rapidly changing AI-driven business and social systems. Generative AI will be the engine of future AI innovation.
Unlocking the Power of Generative AI An Executive's Guide.pdfPremNaraindas1
Generative AI is here, and it can revolutionize your business. With its powerful capabilities, this technology can help companies create more efficient processes, unlock new insights from data, and drive innovation. But how do you make the most of these opportunities?
This guide will provide you with the information and resources needed to understand the ins and outs of Generative AI, so you can make informed decisions and capitalize on the potential. It covers important topics such as strategies for leveraging large language models, optimizing MLOps processes, and best practices for building with Generative AI.
For many decades now, the software industry has attempted to bridge the productivity gap, develop higher quality code and manage the ever growing complexity of software-intensive systems. The results have been mixed, and as a result, a great majority of today's software is still written manually by human developers. This is about to change rapidly as recent developments in the field of Artificial Intelligence show promising results. While artists and designers have been taken by surprise by OpenAI’s DALL-E 2’s capabilities in designing unique art, ChatGPT has astonished the rest of the world with its capability of understanding human interaction. AI-assisted coding solutions such as Github’s Copilot and Replit’s Ghostwriter, among many others, are rapidly developing in a direction where AI generates new code that runs fast with high quality. Little is known about the true capabilities of AI programmers and their impact on the software development industry, education, and research. This talk sheds light on the current state of ChatGPT, large language models including GPT-4, AI-assisted coding, highlights the research gaps, and proposes a way forward.
🔹How will AI-based content-generating tools change your mission and products?
🔹This complimentary webinar [ON-DEMAND] explores multiple use cases that drive adoption in their early adopter customer base to provide product leaders with insights into the future of generative AI-powered businesses, and the potential generative AI holds for driving innovation and improving business processes.
This session was presented at the AWS Community Day in Munich (September 2023). It's for builders that heard the buzz about Generative AI but can’t quite grok it yet. Useful if you are eager to connect the dots on the Generative AI terminology and get a fast start for you to explore further and navigate the space. This session is largely product agnostic and meant to give you the fundamentals to get started.
In this session, you'll get all the answers about how ChatGPT and other GPT-X models can be applied to your current or future project. First, we'll put in order all the terms – OpenAI, GPT-3, ChatGPT, Codex, Dall-E, etc., and explain why Microsoft and Azure are often mentioned in this context. Then, we'll go through the main capabilities of the Azure OpenAI and respective usecases that might inspire you to either optimize your product or build a completely new one.
This presentation presents an overview of the challenges and opportunities of generative artificial intelligence in Web3. It includes a brief research history of generative AI as well as some of its immediate applications in Web3.
Exploring Opportunities in the Generative AI Value Chain.pdfDung Hoang
The article "Exploring Opportunities in the Generative AI Value Chain" by McKinsey & Company's QuantumBlack provides insights into the value created by generative artificial intelligence (AI) and its potential applications.
Retrieval Augmented Generation in Practice: Scalable GenAI platforms with k8s...Mihai Criveti
Mihai is the Principal Architect for Platform Engineering and Technology Solutions at IBM, responsible for Cloud Native and AI Solutions. He is a Red Hat Certified Architect, CKA/CKS, a leader in the IBM Open Innovation community, and advocate for open source development. Mihai is driving the development of Retrieval Augmentation Generation platforms, and solutions for Generative AI at IBM that leverage WatsonX, Vector databases, LangChain, HuggingFace and open source AI models.
Mihai will share lessons learned building Retrieval Augmented Generation, or “Chat with Documents” platforms and APIs that scale, and deploy on Kubernetes. His talk will cover use cases for Generative AI, limitations of Large Language Models, use of RAG, Vector Databases and Fine Tuning to overcome model limitations and build solutions that connect to your data and provide content grounding, limit hallucinations and form the basis of explainable AI. In terms of technology, he will cover LLAMA2, HuggingFace TGIS, SentenceTransformers embedding models using Python, LangChain, and Weaviate and ChromaDB vector databases. He’ll also share tips on writing code using LLM, including building an agent for Ansible and containers.
Scaling factors for Large Language Model Architectures:
• Vector Database: consider sharding and High Availability
• Fine Tuning: collecting data to be used for fine tuning
• Governance and Model Benchmarking: how are you testing your model performance
over time, with different prompts, one-shot, and various parameters
• Chain of Reasoning and Agents
• Caching embeddings and responses
• Personalization and Conversational Memory Database
• Streaming Responses and optimizing performance. A fine tuned 13B model may
perform better than a poor 70B one!
• Calling 3rd party functions or APIs for reasoning or other type of data (ex: LLMs are
terrible at reasoning and prediction, consider calling other models)
• Fallback techniques: fallback to a different model, or default answers
• API scaling techniques, rate limiting, etc.
• Async, streaming and parallelization, multiprocessing, GPU acceleration (including
embeddings), generating your API using OpenAPI, etc.
OpenAI’s GPT 3 Language Model - guest Steve OmohundroNumenta
In this research meeting, guest Stephen Omohundro gave a fascinating talk on GPT-3, the new massive OpenAI Natural Language Processing model. He reviewed the network architecture, training process, and results in the context of past work. There was extensive discussion on the implications for NLP and for Machine Intelligence / AGI.
Link to GPT-3 paper: https://arxiv.org/abs/2005.14165
Link to YouTube recording of Steve's talk: https://youtu.be/0ZVOmBp29E0
‘Big models’: the success and pitfalls of Transformer models in natural langu...Leiden University
Abstract: Large Language Models receive a lot of attention in the media these days. We have all experienced that generative language models of the GPT family are very fluent and can convincingly answer complex questions. But they also have their limitations and pitfalls. In this presentation I will introduce Transformer-based language models, explain the relation between BERT, GPT, and the 130 thousand other models available on https://huggingface.co. I will discuss their use and applications and why they are so powerful. Then I will point out challenges and pitfalls of Large Language Models and the consequences for our daily work and education.
https://bigscience.huggingface.co/
EN: Presentation of the BigScience project: a research initiative launched by HuggingFace and aiming to build a large language model (inspired by OpenAI and GPTx) over multiple languages and a very large processing cluster. The participants plan to investigate the dataset and the model from all angles: bias, social impact, capabilities, limitations, ethics, potential improvements, specific domain performances, carbon impact, general AI/cognitive research landscape.
FR : Présentation du projet Bigscience : un projet de recherche ouvert lancé par HuggingFace et qui a pour objectif de contruire un modèle de langue (ie un peu comme openAI et GPT-3) mais en explorant les problèmes liés au jeux de données et au modèle selon les angles des biais cognitifs, de l'impact social et environemental, des limites éthiques, des possibles gain de performance et de l'impact général de ce type d'approche lorsque le but n'est pas seulement "d'avoir un plus gros modèle".
Give a background of Data Science and Artificial Intelligence, to better understand the current state of the art (SOTA) for Large Language Models (LLMs) and Generative AI. Then start a discussion on the direction things are going in the future.
And then there were ... Large Language ModelsLeon Dohmen
It is not often even in the ICT world that one witnesses a revolution. The rise of the Personal Computer, the rise of mobile telephony and, of course, the rise of the Internet are some of those revolutions. So what is ChatGPT really? Is ChatGPT also such a revolution? And like any revolution, does ChatGPT have its winners and losers? And who are they? How do we ensure that ChatGPT contributes to a positive impulse for "Smart Humanity?".
During a key note om April 3 and 13 2023 Piek Vossen explained the impact of Large Language Models like ChatGPT.
Prof. PhD. Piek Th.J.M. Vossen, is Full professor of Computational Lexicology at the Faculty of Humanities, Department of Language, Literature and Communication (LCC) at VU Amsterdam:
What is ChatGPT? What technology and thought processes underlie it? What are its consequences? What choices are being made? In the presentation, Piek will elaborate on the basic principles behind Large Language Models and how they are used as a basis for Deep Learning in which they are fine-tuned for specific tasks. He will also discuss a specific variant GPT that underlies ChatGPT. It covers what ChatGPT can and cannot do, what it is good for and what the risks are.
An Introduction to Generative AI - May 18, 2023CoriFaklaris1
For this plenary talk at the Charlotte AI Institute for Smarter Learning, Dr. Cori Faklaris introduces her fellow college educators to the exciting world of generative AI tools. She gives a high-level overview of the generative AI landscape and how these tools use machine learning algorithms to generate creative content such as music, art, and text. She then shares some examples of generative AI tools and demonstrate how she has used some of these tools to enhance teaching and learning in the classroom and to boost her productivity in other areas of academic life.
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...David Talby
An April 2023 presentation to the AMIA working group on natural language processing. The talk focuses on three current trends in NLP and how they apply in healthcare: Large language models, No-code, and Responsible AI.
This talk overviews my background as a female data scientist, introduces many types of generative AI, discusses potential use cases, highlights the need for representation in generative AI, and showcases a few tools that currently exist.
The Future of AI is Generative not Discriminative 5/26/2021Steve Omohundro
The deep learning AI revolution has been sweeping the world for a decade now. Deep neural nets are routinely used for tasks like translation, fraud detection, and image classification. PwC estimates that they will create $15.7 trillion/year of value by 2030. But most current networks are "discriminative" in that they directly map inputs to predictions. This type of model requires lots of training examples, doesn't generalize well outside of its training set, creates inscrutable representations, is subject to adversarial examples, and makes knowledge transfer difficult. People, in contrast, can learn from just a few examples, generalize far beyond their experience, and can easily transfer and reuse knowledge. In recent years, new kinds of "generative" AI models have begun to exhibit these desirable human characteristics. They represent the causal generative processes by which the data is created and can be compositional, compact, and directly interpretable. Generative AI systems that assist people can model their needs and desires and interact with empathy. Their adaptability to changing circumstances will likely be required by rapidly changing AI-driven business and social systems. Generative AI will be the engine of future AI innovation.
Unlocking the Power of Generative AI An Executive's Guide.pdfPremNaraindas1
Generative AI is here, and it can revolutionize your business. With its powerful capabilities, this technology can help companies create more efficient processes, unlock new insights from data, and drive innovation. But how do you make the most of these opportunities?
This guide will provide you with the information and resources needed to understand the ins and outs of Generative AI, so you can make informed decisions and capitalize on the potential. It covers important topics such as strategies for leveraging large language models, optimizing MLOps processes, and best practices for building with Generative AI.
For many decades now, the software industry has attempted to bridge the productivity gap, develop higher quality code and manage the ever growing complexity of software-intensive systems. The results have been mixed, and as a result, a great majority of today's software is still written manually by human developers. This is about to change rapidly as recent developments in the field of Artificial Intelligence show promising results. While artists and designers have been taken by surprise by OpenAI’s DALL-E 2’s capabilities in designing unique art, ChatGPT has astonished the rest of the world with its capability of understanding human interaction. AI-assisted coding solutions such as Github’s Copilot and Replit’s Ghostwriter, among many others, are rapidly developing in a direction where AI generates new code that runs fast with high quality. Little is known about the true capabilities of AI programmers and their impact on the software development industry, education, and research. This talk sheds light on the current state of ChatGPT, large language models including GPT-4, AI-assisted coding, highlights the research gaps, and proposes a way forward.
🔹How will AI-based content-generating tools change your mission and products?
🔹This complimentary webinar [ON-DEMAND] explores multiple use cases that drive adoption in their early adopter customer base to provide product leaders with insights into the future of generative AI-powered businesses, and the potential generative AI holds for driving innovation and improving business processes.
This session was presented at the AWS Community Day in Munich (September 2023). It's for builders that heard the buzz about Generative AI but can’t quite grok it yet. Useful if you are eager to connect the dots on the Generative AI terminology and get a fast start for you to explore further and navigate the space. This session is largely product agnostic and meant to give you the fundamentals to get started.
In this session, you'll get all the answers about how ChatGPT and other GPT-X models can be applied to your current or future project. First, we'll put in order all the terms – OpenAI, GPT-3, ChatGPT, Codex, Dall-E, etc., and explain why Microsoft and Azure are often mentioned in this context. Then, we'll go through the main capabilities of the Azure OpenAI and respective usecases that might inspire you to either optimize your product or build a completely new one.
This presentation presents an overview of the challenges and opportunities of generative artificial intelligence in Web3. It includes a brief research history of generative AI as well as some of its immediate applications in Web3.
Exploring Opportunities in the Generative AI Value Chain.pdfDung Hoang
The article "Exploring Opportunities in the Generative AI Value Chain" by McKinsey & Company's QuantumBlack provides insights into the value created by generative artificial intelligence (AI) and its potential applications.
Retrieval Augmented Generation in Practice: Scalable GenAI platforms with k8s...Mihai Criveti
Mihai is the Principal Architect for Platform Engineering and Technology Solutions at IBM, responsible for Cloud Native and AI Solutions. He is a Red Hat Certified Architect, CKA/CKS, a leader in the IBM Open Innovation community, and advocate for open source development. Mihai is driving the development of Retrieval Augmentation Generation platforms, and solutions for Generative AI at IBM that leverage WatsonX, Vector databases, LangChain, HuggingFace and open source AI models.
Mihai will share lessons learned building Retrieval Augmented Generation, or “Chat with Documents” platforms and APIs that scale, and deploy on Kubernetes. His talk will cover use cases for Generative AI, limitations of Large Language Models, use of RAG, Vector Databases and Fine Tuning to overcome model limitations and build solutions that connect to your data and provide content grounding, limit hallucinations and form the basis of explainable AI. In terms of technology, he will cover LLAMA2, HuggingFace TGIS, SentenceTransformers embedding models using Python, LangChain, and Weaviate and ChromaDB vector databases. He’ll also share tips on writing code using LLM, including building an agent for Ansible and containers.
Scaling factors for Large Language Model Architectures:
• Vector Database: consider sharding and High Availability
• Fine Tuning: collecting data to be used for fine tuning
• Governance and Model Benchmarking: how are you testing your model performance
over time, with different prompts, one-shot, and various parameters
• Chain of Reasoning and Agents
• Caching embeddings and responses
• Personalization and Conversational Memory Database
• Streaming Responses and optimizing performance. A fine tuned 13B model may
perform better than a poor 70B one!
• Calling 3rd party functions or APIs for reasoning or other type of data (ex: LLMs are
terrible at reasoning and prediction, consider calling other models)
• Fallback techniques: fallback to a different model, or default answers
• API scaling techniques, rate limiting, etc.
• Async, streaming and parallelization, multiprocessing, GPU acceleration (including
embeddings), generating your API using OpenAPI, etc.
OpenAI’s GPT 3 Language Model - guest Steve OmohundroNumenta
In this research meeting, guest Stephen Omohundro gave a fascinating talk on GPT-3, the new massive OpenAI Natural Language Processing model. He reviewed the network architecture, training process, and results in the context of past work. There was extensive discussion on the implications for NLP and for Machine Intelligence / AGI.
Link to GPT-3 paper: https://arxiv.org/abs/2005.14165
Link to YouTube recording of Steve's talk: https://youtu.be/0ZVOmBp29E0
‘Big models’: the success and pitfalls of Transformer models in natural langu...Leiden University
Abstract: Large Language Models receive a lot of attention in the media these days. We have all experienced that generative language models of the GPT family are very fluent and can convincingly answer complex questions. But they also have their limitations and pitfalls. In this presentation I will introduce Transformer-based language models, explain the relation between BERT, GPT, and the 130 thousand other models available on https://huggingface.co. I will discuss their use and applications and why they are so powerful. Then I will point out challenges and pitfalls of Large Language Models and the consequences for our daily work and education.
https://bigscience.huggingface.co/
EN: Presentation of the BigScience project: a research initiative launched by HuggingFace and aiming to build a large language model (inspired by OpenAI and GPTx) over multiple languages and a very large processing cluster. The participants plan to investigate the dataset and the model from all angles: bias, social impact, capabilities, limitations, ethics, potential improvements, specific domain performances, carbon impact, general AI/cognitive research landscape.
FR : Présentation du projet Bigscience : un projet de recherche ouvert lancé par HuggingFace et qui a pour objectif de contruire un modèle de langue (ie un peu comme openAI et GPT-3) mais en explorant les problèmes liés au jeux de données et au modèle selon les angles des biais cognitifs, de l'impact social et environemental, des limites éthiques, des possibles gain de performance et de l'impact général de ce type d'approche lorsque le but n'est pas seulement "d'avoir un plus gros modèle".
Give a background of Data Science and Artificial Intelligence, to better understand the current state of the art (SOTA) for Large Language Models (LLMs) and Generative AI. Then start a discussion on the direction things are going in the future.
What does Generative AI mean for public policy?Sam Gilbert
The instant popularity of AI tools like ChatGPT and Stable Diffusion has seen so-called "Generative AI" supplant the metaverse as the hottest trend in tech.
But is the technology really significant, or is it mostly hype?
Focusing on OpenAI's large languages models (LLMs), this presentation by Sam Gilbert to the University of Cambridge's Bennett Institute explores the potential public policy implications of Generative AI -- and how policymakers and policy researchers can use it in their own work.
Past, Present and Future of Generative AIabhishek36461
Generative AI creates new content (images, text, music) based on learned patterns.
It learns from vast examples and can produce original, unseen works.
Capable of blending learned elements to generate unique outputs.
Can produce customized creations based on specific prompts.
Improves and refines its output over time with more data and feedback.
This paper analyses ChatGPT 3.5 Turbo, the latest free version of the ChatGPT service. By using
ChatGPT to create theoretical papers on itself, further insights are gained into the potential of ChatGPT
and other generative artificial intelligence services as well as their weaknesses. Through this analysis
presented, potential future avenues of research are suggested alongside necessary changes if services like
ChatGPT wish to be used as a tool in academic works.
This paper analyses ChatGPT 3.5 Turbo, the latest free version of the ChatGPT service. By using
ChatGPT to create theoretical papers on itself, further insights are gained into the potential of ChatGPT
and other generative artificial intelligence services as well as their weaknesses. Through this analysis
presented, potential future avenues of research are suggested alongside necessary changes if services like
ChatGPT wish to be used as a tool in academic works.
Artificial intelligence (AI) is a multidisciplinary field of science and engineering whose goal is to create intelligent machines.
We believe that AI will be a force multiplier on technological progress in our increasingly digital, data-driven world. This is because everything around us today, ranging from culture to consumer products, is a product of intelligence.
The State of AI Report is now in its sixth year. Consider this report as a compilation of the most interesting things we’ve seen with a goal of triggering an informed conversation about the state of AI and its implication for the future.
We consider the following key dimensions in our report:
Research: Technology breakthroughs and their capabilities.
Industry: Areas of commercial application for AI and its business impact.
Politics: Regulation of AI, its economic implications and the evolving geopolitics of AI.
Safety: Identifying and mitigating catastrophic risks that highly-capable future AI systems could pose to us.
Predictions: What we believe will happen in the next 12 months and a 2022 performance review to keep us honest.
Produced by Nathan Benaich and Air Street Capital team
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?Bernard Marr
Could GPT-3 be the most powerful artificial intelligence ever developed? When OpenAI, a research business co-founded by Elson Musk, released the tool recently, it created a massive amount of hype. Here we look through the hype and outline what it is and what it isn’t.
Benefiting from Semantic AI along the data life cycleMartin Kaltenböck
Slides of 1 hour session of Martin Kaltenböck (CFO and Managing Partner of Semantic Web Company / PoolParty Software Ltd) on 19 March 2019 in Boston, US at the Enterprise Data World 2019, with its title: Benefiting from Semantic AI along the data life cycle.
State of AI Report 2023 - ONLINE presentationssuser2750ef
State of AI Report 2023 - ONLINE.pptx
When conducting a PEST analysis for the Syrian conflict, it's important to consider the political, economic, socio-cultural, and technological factors that have influenced and continue to impact the situation in Syria. Here's a high-level overview of a PEST analysis for the Syrian conflict:
1. Political Factors:
- Government Instability: Ongoing civil war and conflict have led to political instability and a complex power struggle between various factions and international players.
- Foreign Intervention: Involvement of external powers and regional actors has exacerbated the conflict and added geopolitical complexities to the situation.
- International Relations: Relations with global powers like the United States, Russia, and regional players like Iran and Turkey significantly impact the conflict dynamics.
2. Economic Factors:
- Humanitarian Crisis: The conflict has resulted in a severe humanitarian crisis, causing widespread displacement, destruction of infrastructure, and economic decline.
- Sanctions and Trade Barriers: International sanctions and disrupted trade have further worsened the economic situation in Syria, affecting the livelihoods of the population.
- Resource Depletion: Conflict-driven resource depletion, including loss of agricultural lands and disruption of industries, has weakened the economy.
3. Socio-cultural Factors:
- Civilian Suffering: The conflict has led to a significant loss of life, displacement of populations, and severe trauma among civilians, impacting social cohesion and community structures.
- Ethnic and Religious Divisions: Deep-seated ethnic and religious divisions have fueled the conflict, leading to sectarian tensions and societal fragmentation.
- Refugee Crisis: The conflict has triggered a massive refugee crisis, with millions of Syrians seeking asylum in neighboring countries and beyond, straining regional stability.
4. Technological Factors:
- Communication and Propaganda: Technology, including social media, has been used for communication, mobilization, and spreading propaganda by various actors in the conflict.
- Warfare Technology: Advancements in warfare technology and the use of drones, cyber warfare, and other advanced weaponry have transformed the nature of conflict in Syria.
- Cybersecurity Concerns: The conflict has also raised concerns about cybersecurity threats, misinformation campaigns, and digital vulnerabilities in the region.
This analysis provides a broad understanding of the multifaceted nature of the Syrian conflict, highlighting the diverse factors at play and the complex challenges facing Syria and the international community.
Genetic Algorithms and Programming - An Evolutionary Methodologyacijjournal
Genetic programming (GP) is an automated method for creating a working computer program from a high-level problem statement of a problem. Genetic programming starts from a high-level statement of “what needs to be done” and automatically creates a computer program to solve the problem. In artificial intelligence, genetic programming (GP) is an evolutionary algorithm-based methodology inspired by biological evolution to find computer programs that perform a user defined task. It is a specialization of genetic algorithms (GA) where each individual is a computer program. It is a machine learning technique used to optimize a population of computer programs according to a fitness span determined by a program's ability to perform a given computational task. This paper presents a idea of the various principles of genetic programming which includes, relative effectiveness of mutation, crossover, breeding computer programs and fitness test in genetic programming. The literature of traditional genetic algorithms contains related studies, but through GP, it saves time by freeing the human from having to design complex algorithms. Not only designing the algorithms but creating ones that give optimal solutions than traditional counterparts in noteworthy ways.
Explore our comprehensive data analysis project presentation on predicting product ad campaign performance. Learn how data-driven insights can optimize your marketing strategies and enhance campaign effectiveness. Perfect for professionals and students looking to understand the power of data analysis in advertising. for more details visit: https://bostoninstituteofanalytics.org/data-science-and-artificial-intelligence/
Opendatabay - Open Data Marketplace.pptxOpendatabay
Opendatabay.com unlocks the power of data for everyone. Open Data Marketplace fosters a collaborative hub for data enthusiasts to explore, share, and contribute to a vast collection of datasets.
First ever open hub for data enthusiasts to collaborate and innovate. A platform to explore, share, and contribute to a vast collection of datasets. Through robust quality control and innovative technologies like blockchain verification, opendatabay ensures the authenticity and reliability of datasets, empowering users to make data-driven decisions with confidence. Leverage cutting-edge AI technologies to enhance the data exploration, analysis, and discovery experience.
From intelligent search and recommendations to automated data productisation and quotation, Opendatabay AI-driven features streamline the data workflow. Finding the data you need shouldn't be a complex. Opendatabay simplifies the data acquisition process with an intuitive interface and robust search tools. Effortlessly explore, discover, and access the data you need, allowing you to focus on extracting valuable insights. Opendatabay breaks new ground with a dedicated, AI-generated, synthetic datasets.
Leverage these privacy-preserving datasets for training and testing AI models without compromising sensitive information. Opendatabay prioritizes transparency by providing detailed metadata, provenance information, and usage guidelines for each dataset, ensuring users have a comprehensive understanding of the data they're working with. By leveraging a powerful combination of distributed ledger technology and rigorous third-party audits Opendatabay ensures the authenticity and reliability of every dataset. Security is at the core of Opendatabay. Marketplace implements stringent security measures, including encryption, access controls, and regular vulnerability assessments, to safeguard your data and protect your privacy.
2. 1966: ELIZA
Image source: en.wikipedia.org/wiki/ELIZA#/media/File:ELIZA_conversation.png
“While ELIZA was capable of
engaging in discourse, it
could not converse with true
understanding. However,
many early users were
convinced of ELIZA's
intelligence and
understanding, despite
Weizenbaum's insistence to
the contrary.”
Source: en.wikipedia.org/wiki/ELIZA (and
references therein).
3. 2005: SCIgen - An Automatic CS Paper Generator
nature.com/articles/d41586-021-01436-7
news.mit.edu/2015/how-three-mit-students-fooled-scientific-journals-0414
A project using a rather rudimentary technology that aimed to "maximize amusement, rather than coherence" is
still the cause of troubles today...
pdos.csail.mit.edu/archive/scigen
4. 2017: Google Revolutionized Text Generation
■ Vaswani (2017), Attention Is All You Need (doi.org/10.48550/arXiv.1706.03762)
■ openai.com/research/better-language-models
Image generated with DALL.E: “A small robot standing on the
shoulder of a giant robot” (and slightly modified with The Gimp)
OpenAI’s Generative Pre-trained
Transformer (DALL.E, 2021; ChatGPT,
2022), as the name suggests, reposes on
Transformers.
Google introduced the Transformer,
which rapidly became the state-of-the-art
approach to solve most NLP problems.
5. ● Kiela et al. (2021), Dynabench: Rethinking Benchmarking in NLP: arxiv.org/abs/2104.14337
● Roser (2022), The brief history of artificial intelligence: The world has changed fast – what might be next?: ourworldindata.org/brief-history-of-ai
Transformers
2017
Text and shapes in blue have been added to the original work from Max Roser.
6. What Are Transformers?
Source: Vaswani (2017), Attention Is All You Need
(doi.org/10.48550/arXiv.1706.03762)
Generative (deep learning) models for understanding and generating text,
images and many other types of data.
Transformers analyze chunks of data, called "tokens" and learn to predict
the next token in a sequence, based on previous and, if available, following
tokens.
The auto-regressive concept means that the output of the model, such as
the prediction of a word in a sentence, is influenced by the previous words it
has generated.
Music—MusicLM (Google) and Jukebox (OpenAI) generate music from text.
Image—Imagen (Google) and DALL.E (OpenAI) generate novel images from text.
Texte—OpenAI’s GPT has become widely known, but other players have similar technology
(including Google, Meta, Anthropic and others).
Others—Recommender (movies, books, flight destinations), drug discovery…
Models that learn from a given dataset how to
generate new data instances.
7. 2022: ChatGPT
“ChatGPT, the popular chatbot
from OpenAI, is estimated to have
reached 100 million monthly
active users in January, just two
months after launch, making it the
fastest-growing consumer
application in history”
statista.com/chart/29174/time-to-one-million-users
Reuters, Feb 1, 2023
https://reut.rs/3yQNlGo
8. The Mushrooming of Transformer-Based LLMs
PaML (540b), LaMDA
(137b) and others.
OPT-IML (175b), Galactica
(120b), BlenderBot3
(175b), Llama 2 (70b)
ERNIE 3.0 Titan (260b)
GPT-3 (175b), GPT-3.5 (?b),
GPT-4 (?b)
BLOOM (176b)
PanGu-𝛼 (200b)
Jurassic-1 (178b), Jurassic-2 (?b)
Exaone (300b)
Megatron-Turing NLG (530b)
(It appears that all those models rely only on
transformer-based decoders)
Claude (?b), Claude 2 (?b)
12. AI Mentions Boost Stock Prices
● AI-mentioning companies:
+4.6% avg. stock price
increase (nearly double of the
non-mentioning).
● In general, 67% of companies
that mentioned AI observed an
increase in their stock prices
→ +8.5% on average.
● Tech companies:
71% → +11.9% on avg.
● Non-tech companies:
65% → +6.8% on avg.
- Mentions of "AI" and related terms (machine learning, automation, robots, etc.).
- S&P 500 companies in 2023.
- 3-day change from the date the earnings call transcript was published. Source: wallstreetzen.com/blog/ai-mention-moves-stock-prices-2023
13. GPUs Demand Skyrockets
Before LLMs, GPUs were primarily needed for training, and
CPUs were used for inference. However, with the emergence
of LLMs, GPUs have become almost essential for both tasks.
Paraphrasing Brannin McBee, co-founder of CoreWeave, in
Bloomberg Podcast*:
While you may train the model using 10,000 GPUs, the real
challenge arises when you need 1 million GPUs to meet the
entire inference demand. This surge in demand is expected
during the initial one to two years after the launch, and it's likely
to keep growing thereafter.
* How to Build the Ultimate GPU Cloud to Power AI | Odd Lots (youtube.com/watch?v=9OOn6u6GIqk&t=1308s)
14. Enhancing Productivity With Generative AI?
nature.com/articles/d41586-023-02270-9
science.org/doi/10.1126/science.adh2586
15. McKinsey & Goldman Are Rather Bullish
mckinsey.com/mgi/overview/in-the-news/ai-
could-increase-corporate-profits-by-4-trillion-
a-year-according-to-new-research
goldmansachs.com/intelligence/pages/gene
rative-ai-could-raise-global-gdp-by-7-percent.
html
16. ● AT&T started to investigate “Mobile
Telephony” in 1980.
● McKinsey projected then that the size
of mobile phone market in 2000
should be < 1 Million subscribers.
● It turned out that the size was > 120
Million, and several billion today…
Sources:
● Cutting the cord, economist.com/node/246152
● Statistics, itu.int/en/ITU-D/Statistics/Pages/stat/default.aspx
● Danny Ralph & Marc Jansen, Lecture Slides 2015, Management Science, Judge Business School, The University of Cambridge, UK
Forecasts by Big Names Are Not Always Reliable
18. Beware of “Hallucinations” Which Do Remain Very Real
“Hallucinations” are “confident
statements that are not true”1
.
For the moment, this
phenomenon inexorably
affects all known LLMs.
1: fr.wikipedia.org/wiki/Hallucination_(intelligence_artificielle)
Yves Montand in “Le Cercle Rouge” during an attack of delirium tremens
This thing probably doesn't exist.
19. Concrete
Hallucinations (GPT-4)
We asked ChatGPT the first part of the third
question of the British Mathematical Olympiad
1977: bmos.ukmt.org.uk/home/bmo-1977.pdf
Is that so? Although not an obvious
hallucination, it may remind us of Fermat’s
lack of space in the margin to give the proof
of his last theorem… Perhaps here there is a
lack of tokens?
Here a total hallucination, this statement is
evidently false.
Perhaps it meant “the
product of two negative
numbers”
Here a total hallucination, this statement is
evidently false. (Although in this case the
inequality is indeed clearly true.)
20. The Saga of the Lawyer Who Used ChatGPT
nytimes.com/2023/06/08/nyregion/law
yer-chatgpt-sanctions.html
nytimes.com/2023/05/27/nyregion/avia
nca-airline-lawsuit-chatgpt.html
nytimes.com/2023/06/22/nyregion/la
wyers-chatgpt-schwartz-loduca.html
21. ChatGPT: Achieving Human-Level Performance in
Professional and Academic Benchmarks
● GPT-4's performance in recent tests is
undeniably impressive.
● Study conducted by OpenAI
(openai.com/papers/gpt-4.pdf).
● Most of those tests mainly focus on high
school-level content.
● Many are prepared through test prep
courses and resources.
● By contrast, university exams typically
require a deeper understanding of course
material and critical thinking skills.
● Uniform Bar Exam: Worth noting, but
potential overestimation concerns (see
dx.doi.org/10.2139/ssrn.4441311).
22. Exploring the MIT Mathematics and EECS Curriculum Using
Large Language Models
Published on Jun 15, 2023
Authors: Sarah J. Zhang, Samuel Florin, Ariel N. Lee, Eamon Niknafs, Andrei Marginean, Annie Wang, Keith
Tyser, Zad Chin, Yann Hicke, Nikhil Singh, Madeleine Udell, Yoon Kim, Tonio Buonassisi, Armando
Solar-Lezama, Iddo Drori
Abstract
We curate a comprehensive dataset of 4,550 questions and solutions from problem sets,
midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and
Computer Science (EECS) courses required for obtaining a degree. We evaluate the ability of
large language models to fulfill the graduation requirements for any MIT major in Mathematics
and EECS. Our results demonstrate that GPT-3.5 successfully solves a third of the entire MIT
curriculum, while GPT-4, with prompt engineering, achieves a perfect solve rate on a test set
excluding questions based on images. We fine-tune an open-source large language model on
this dataset. We employ GPT-4 to automatically grade model responses, providing a detailed
performance breakdown by course, question, and answer type. By embedding questions in a
low-dimensional space, we explore the relationships between questions, topics, and classes and
discover which questions and classes are required for solving other questions and classes
through few-shot learning. Our analysis offers valuable insights into course prerequisites and
curriculum design, highlighting language models' potential for learning and improving
Mathematics and EECS education.
Source: arxiv.org/abs/2306.08997
i.e., GPT-4
scored 100% on
MIT EECS
Curriculum
(Electrical
Engineering and
Computer
Science)
23. “No, GPT4 can’t ace MIT”
Three MIT undergrads have debunked the myth.
- 4% of the questions were unsolvable. (How did GPT-4 achieve 100%?)
- Information leak in some few-shot prompts: for those, the answer was
quasi-given in the question.
- The automatic grading using GPT-4 itself has some severe issues: prompt
cascade that reprompted (many times) when the given answer was deemed
incorrect. 16% of the questions were multi-choices questions, hence a
quasi-guaranteed correct response.
- Bugs found in the research script that raise serious questions regarding the
soundness of the study.
Source: flower-nutria-41d.notion.site/No-GPT4-can-t-ace-MIT-b27e6796ab5a48368127a98216c76864
Note: The paper has since been withdrawn (see official statement at people.csail.mit.edu/asolar/CoursesPaperStatement.pdf)
24. Chemistry May Not Be ChatGPT Cup of Tea
A study conducted by three researchers of the University of
Hertfordshire (UK) showed that ChatGPT is not a fan of
chemistry.
Real exams were used, and the authors note that “[a] well-written
question item aims to create intellectual challenge and to require
interpretation and inquiry. Questions that cannot be easily
‘Googled’ or easily answered through a single click in an
internet search engine is a focus.”
“The overall grade on the year 1 paper calculated from the top
four graded answers would be 34.1%, which does not meet the
pass criteria. The overall grade on the year 2 paper would be
18.3%, which does not meet the pass criteria.”
Source: Fergus et al., 2023, Evaluating Academic Answers Generated Using ChatGPT (pubs.acs.org/doi/10.1021/acs.jchemed.3c00087)
25. The “Drift” Phenomenon
Sources:
- wsj.com/articles/chatgpt-openai-math-artificial-intelligence-8aba83f0
- Chaîne et al., 2023, arxiv.org/abs/2307.09009
● New research from Stanford and UC Berkeley
highlights a fundamental challenge in AI
development: "drift."
● Drift occurs when improving one aspect of
complex AI models leads to a decline in
performance in other areas.
● ChatGPT has shown deterioration in basic math
operations despite advancements in other tasks.
● GPT-4 exhibits reduced responsiveness to
chain-of-thought prompting (may be intended to
mitigate potential misuse with malicious
prompts).
The “behavior of the ‘same’ LLM service can
change substantially in a relatively short amount of
time, highlighting the need for continuous monitoring
of LLMs” (Chain et al., 2023).
27. First We Must Have a Problem to Solve…
Source: DeepLearning.AI, licensed under CC BY-SA 2.0
28. Then We Need a Model
Commercial APIs
- Google, OpenAI, Anthropic, Microsoft...
- Privacy concerns may arise.
- No specific hardware requirement.
- Prompt engineering (OpenAI offers prompt fine-tuning).
Use a foundation model (many open sources models are available)
- As it is (prompt engineering),
- or fine-tuned (either full or parameter efficient fine-tuning).
- May required specific hardware/infrastructure for hosting, fine-tuning and
inferences.
Train a model from the scratch
- Requires huge resources (both data and computing power).
- (e.g., BloombergGPT, arxiv.org/abs/2303.17564.)
29. A Plethora of Open
Source Pre-Trained
Models
huggingface.co/models
Models should be selected
depending on:
● The problem at hand.
● The strength of the model.
● The operating costs (larger
models require more
resources).
● Other considerations (e.g.,
license).
30. Prompt Engineering: “Query Crafting”
Improving the output with actions like phrasing
queries, specifying styles, providing context, or
assigning roles (e.g., 'Act as a mathematics
teacher') (Wikipedia, 2023).
Some hints can be found in OpenAI’s “GPT best
practices” (OpenAi, 2023).
Chain-of-thought: popular technique consisting
in “guiding [LLMs] to produce a sequence of
intermediate steps before giving the final answer”
(Wei et al., 2022).
Sources:
- Wei, J.et al., 2022. Emergent abilities of large language models, arxiv.org/abs/2206.07682
- OpenAI, 2023, platform.openai.com/docs/guides/gpt-best-practices/six-strategies-for-getting-better-results
- Wikipedia, 2023, , Prompt Engineering, en.wikipedia.org/wiki/Prompt_engineering
(graph from Wei et al., 2022)
About GSM8K benchmark: arxiv.org/abs/2110.14168
31. Prompt Engineering: In-Context Learning (ICL)
In-Context Learning (ICL) consists in “a few input-output
examples in the model’s context (input) as a preamble
before asking the model to perform the task for an unseen
inference-time example” (Wei et al., 2022).
It is a kind of “ephemeral supervised learning.”
- Zero-shot prompting or Zero-shot learning: no example
given (for largest LLMs, smaller ones may struggle).
- One-shot prompting: one example provided.
- Few-shot prompting: a few examples (typically 3~6).
⚠ Context window limits (e.g., 4096 tokens).
Tweet: @lufthansa Please find our
missing luggage!!
Sentiment: negative
Tweet: Will be on LH to FRA very soon.
Cheers!
Sentiment: positive
Tweet: Refused to compensate me for 2
days cancelled flights . Joke of a airline
Sentiment:
LLM
negative
Example of an input and
output for two-shot prompting
Source: Wei, J.et al., 2022. Emergent abilities of large language models, arxiv.org/abs/2206.07682
32. Fine-Tuning: Introduction
Few shot learning:
- May not be sufficient for smaller models.
- Consumes tokens from the context window.
Fine-tuning is a supervised learning process
that leads to a new model (in contrast with
in-context learning that is “ephemeral”).
Task specific prompt-completion pairs data are
required.
Base LLM
Fine-tuned
LLM
(Prompt_1, completion_1)
(Prompt_2, completion_2)
…
(Prompt_n, completion_n)
Task specific prompt-completion
pairs data
33. Full Fine-Tuning: Updating All Parameters
Fine-tuning very often means “instruction fine-tuning.”
Instruction fine-tuning: each prompt-completion pair includes a specific
instruction (summarize this, translate that, classify this tweet, …).
● Fine-tuning on a single task (e.g, summarization) may lead to a phenomenon
referred to as “catastrophic forgetting” (arxiv.org/pdf/1911.00202), where the
model loses its abilities on other tasks (may not be a business issue, though).
● Fine-tuning on multi tasks (e.g., summarization, translation, classification, …).
This requires a lot more training data. (E.g., see FLAN in Wei et al., 2022.)
Full fine-tuning is extremely resources demanding, even more so for large models.
Source: Wei et al., 2022, Finetuned Language Models Are Zero-Shot Learners. arxiv.org/abs/2109.01652
34. Parameter Efficient Fine-Tuning (PEFT)
Unlike full fine-tuning, PEFT preserves the vast majority of the weights of the original
model.
● Less prone to “catastrophic forgetting” on single task.
● Often a single GPU is enough.
Three methods:
● Selective—subset of initial params to fine-tune.
● Reparameterization—reparameterize model weights using a low-rank
representation, e.g., LoRA (Hu et al., 2021).
● Additive—add trainable layers or parameters to model, two approaches:
- Adapters: add new trainable layers to the architecture of the model.
- Soft prompts: focus on manipulating the input (this is not prompt engineering).
Source:
- coursera.org/learn/generative-ai-with-llms/lecture/rCE9r/parameter-efficient-fine-tuning-peft
- Hu et al., 2021, LoRA: Low-Rank Adaptation of Large Language Models. arxiv.org/abs/2106.09685
35. OpenAI API offers
prompt tuning for
gpt-3.5-turbo, but not
“yet” for GPT-4.
platform.openai.com/docs/guides/fine-tuning
Fine-Tuning With
OpenAI GPT
(PEFT)
36. Reinforcement Learning From Human Feedback
LLMs are trained on the web data with a lot of irrelevant matters (unhelpful), or worse,
where false (dishonest) and/or harmful information are abundant, e.g.,
● Potentially dangerous false medical advices.
● Valid techniques for illegal activities (hacking, deceiving, building weapons, …).
HHH (Helpful, Honest & Harmless) alignment (Askell et al., 2021): ensuring that the
model's behavior and outputs are consistent with human values, intentions, and ethical
standards.
Reinforcement Learning from Human Feedback, or RLHF (Casper et al., 2023)
● “is a technique for training AI systems to align with human goals.”
● “[It] has emerged as the central method used to finetune state-of-the-art [LLMs].”
● It reposes on human judgment and consensus.
Source:
- Casper et al., 2023, Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. arxiv.org/abs/2307.15217
- Ziegler et al., 2022, Fine-Tuning Language Models from Human Preferences. arxiv.org/abs/1909.08593
- Askell et al., 2021, A General Language Assistant as a Laboratory for Alignment. arxiv.org/abs/2112.00861
37. What Is RLHF by Sam Altman
5:59
What is RLHF? Reinforcement Learning with Human Feedback, …
6:07
… So, we trained these models on a lot of text data and, in that process, they
learned the underlying, …. And they can do amazing things.
6:26
But when you first play with that base model, that we call it, after you finish
training, … it can do a lot of, you know, there's knowledge in there. But it's not
very useful or, at least, it's not easy to use, let's say. And RLHF is how we
take some human feedback,
6:45
the simplest version of this is show two outputs, ask which one is better
than the other,
6:50
which one the human raters prefer, and then feed that back into the model
with reinforcement learning.
6:56
And that process works remarkably well with, in my opinion, remarkably little
data to make the model more useful. So, RLHF is how we align the model to
what humans want it to do.
Sam Altman: OpenAI CEO on
GPT-4, ChatGPT, and the Future of
AI | Lex Fridman Podcast #367
(youtu.be/L_Guz73e6fw?si=vfkdtN
CyrQa1RzZR&t=359)
38. Source: Liu et al., 2022, Aligning Generative Language Models with Human Values. aclanthology.org/2022.findings-naacl.18
RLHF: Example of Alignment Tasks
39. RLHF Illustration
Source: Lambert et al., 2022, Illustrating Reinforcement Learning from Human Feedback (RLHF). huggingface.co/blog/rlhf
Images copied from huggingface.co/blog/rlhf
41. Assessing and Comparing LLMs
Metrics while training the model—ROUGE (summary) or BLEU (translation).
Benchmarks—A non-exhaustive list:
- ARC (Abstraction and Reasoning Corpus, arxiv.org/pdf/2305.18354),
- HellaSwag (arxiv.org/abs/1905.07830),
- TruthfulQA (arxiv.org/abs/2109.07958),
- GLUE & SuperGLUE (General Language Understanding Evaluation, gluebenchmark.com),
- HELM (Holistic Evaluation of Language Models, crfm.stanford.edu/helm),
- MMLU (Massive Multitask Language Understanding, arxiv.org/abs/2009.03300),
- BIG-bench (arxiv.org/pdf/2206.04615).
Others—“Auto-Eval of Question-Answering Tasks”
(blog.langchain.dev/auto-eval-of-question-answering-tasks).
42. Source: Wu et al., 2023,
BloombergGPT: A Large Language
Model for Finance.
arxiv.org/abs/2303.17564 (Table 13:
“BIG-bench hard results using
standard 3-shot prompting”)
43. Source: Touvron et al., 2023, Llama 2: Open Foundation and Fine-Tuned Chat Models,
scontent-fra3-1.xx.fbcdn.net/v/t39.2365-6/10000000_662098952474184_2584067087619170692_n.pdf
46. Question ChatGPT About the Latest Financial
Reports?
—blog.langchain.dev/tutorial-
chatgpt-over-your-data
“[ChatGPT] doesn’t know about
your private data, it doesn’t know
about recent sources of data.
Wouldn’t it be useful if it did?”
47. Workflow Overview
Question
Answer
« Quels vont être les dividendes payés
par action par le Groupe Crit ? »
« Le Groupe CRIT proposera lors de sa prochaine Assemblée Générale, le 9
juin 2023, le versement d'un dividende exceptionnel de 3,5 € par action. »
The example (the question and associated
answer) is a real example (the LLM was
“gpt-3.5-turbo” from OpenAI)
Technique described in: Lewis et al., 2020.
Retrieval-augmented generation for knowledge-intensive
nlp tasks. (doi.org/10.48550/arXiv.2005.11401)
Extracting
relevant
information
(“context”)
Generate a prompt
accordingly
(“question +
context”)
LLM
Vector store
Split into chunks
1
2 3
Compute
embeddings
48. Preliminary Prototype
Financial reports retrieved directly from the French AMF (“Autorité
des marchés financiers”) via its API (info-financiere.fr).
xhtml document in
French language.
Question and answer
are in English (they
would be in French
should the question be
asked in French).
49. Except where otherwise noted, this work is licensed under
https://creativecommons.org/licenses/by/4.0/
619.io