Digital Method of the Month: What LLMs Can and Cannot Do

Hybrid 

Have you seen a presentation on digital research methods and wondered if they are applicable to your work? Are you interested in learning new digital skills but unsure where to start?    

This is the right place for you!    

The digital method of the month meeting is a safe space to freely discuss the practicalities of learning and implementing a new digital skill in your research.    

Each month we select a method, and we have an honest and practical discussion on what it takes to learn and master it. How much time will it take to get the basics? What are the software options available? What are the most common pitfalls? Where can you find more info on the subject? etc...     

The method of this month is Large Language Models (LLMs). LLMs are a type of artificial intelligence trained on vast amounts of text data to generate human-like text and understand natural language. They can summarise articles, draft emails, or assist in complex analyses. However, they have limitations: LLMs can sometimes provide confident-sounding but incorrect responses, struggle with domain-specific expertise, and depend heavily on the quality of their training data. During the meeting, we will introduce the concept of LLMs, discuss their strengths and weaknesses, and explore how they can be effectively integrated into research workflows. Join us to learn more! 

This conversation will be led by Chris Oldnall and Martin Disley  

After taking part in this event, you may decide that you need some further help in applying what you have learnt to your research. If so, you can book a Data Surgery meeting with one of our training fellows.  

More details about Data Surgeries.  

Those who have registered to take part will receive an email with full details on how to get ready for this course.  

If you’re new to this training event format, or to CDCS training events in general, read more on what to expect from CDCS training. Here you will also find details of our cancellation and no-show policy, which applies to this event.  

Level   

This is a beginner-friendly course. No previous knowledge on the topic is required/expected, and the trainer will cover the basics of the method.    

Learning Outcomes  

• To engage in discussions about what Large Language Models can and cannot be used for.
• To have access to a source of information and online materials on the use of Large Language Models. 

Skills   

By attending this course, you will familiarise yourself with the following skills  

• Understanding the uses and limitations of LLMs

Explore More Training

• Silent Disco: Computer Vision for the Humanities: An Introduction to Deep Learning for Image Classification
• Using Prompting Efficiently for Research
• Text Classification in Practice: From Topic Models to Transformers

Return to the Training Homepage to see other available events