Welcome to the LLMs for Exploratory Research workshop.
In a fast evolving artificial intelligence landscape, LLMs such as GPT have become ubiquitous. In the research community, their advantages and pitfalls are hotly debated. In this workshop, we will explore different chatbots powered by LLMs. Our main goal will be to understand how LLMs can be used by researchers to conduct early-stage (or exploratory) research. Throughout the workshop, we will discuss best practices for prompt engineering and heuristics to evaluate the suitability of an LLM's output for our research purposes. Though the workshop primarily focuses on early-stage research, we will briefly discuss the use cases of LLMs in later stages of research, such as data analysis and writing.
This repository contains the materials for D-Lab LLMs for Exploratory Research workshop.
No prior experience in using LLMs is necessary for this workshop.
Check D-Lab's Learning Pathways to figure out which of our workshops to take!
In this workshop, we assess the different uses of LLMs in exploratory research and discusses ways to evaluate strengths and weaknesses of LLMs in various phases of exploratory research. First, we’ll cover some of the different types of LLMs that can be useful for research. Then, we’ll explore the use cases of LLMs specifically for exploratory research. As we go along, we will discuss the strengths and limitations of using LLMs for research.
After this workshop, you will be able to:
- Use LLMs for tasks related to exploratory research.
- Compare and contrast outputs from different LLMs.
This workshop does not cover the following:
- How to use LLMs for coding. These are covered in Copilot Fundamentals.
- Introduction to GPT models. These are covered in Python GPT Fundamentals.
We will be using the following LLM-chatbots during the workshop. You can create accounts for each by following the links:
- ChatGPT
- Perplexity
- You can create a free Perplexity Pro account using your Berkeley email address.
- Phind
- Claude.ai
You can view the workshop materials on GitHub and download the paper from the repository.
D-Lab works with Berkeley faculty, research staff, and students to advance data-intensive social science and humanities research. Our goal at D-Lab is to provide practical training, staff support, resources, and space to enable you to use R for your own research applications. Our services cater to all skill levels and no programming, statistical, or computer science backgrounds are necessary. We offer these services in the form of workshops, one-to-one consulting, and working groups that cover a variety of research topics, digital tools, and programming languages.
Visit the D-Lab homepage to learn more about us. You can view our calendar for upcoming events, learn about how to utilize our consulting and data services, and check out upcoming workshops.
Here are other LLM/GPT workshops offered by the D-Lab: