Automating Topic Discovery with LLMs

Anand S (~anand40)




This talk explores how we can automatically identify topics from text using LLMs. We will group the text into clusters, find an apt topic name for each cluster, and match each piece of text to the right topic, and visualize these.

We'll cover:

  • Introduction to Topic Modeling: Understand topic modeling and how it helps
  • Using LLMs for Topic Discovery: How LLMs create embeddings, how you can K-Means cluster them, name them automatically, and then classify using a dot product
  • Applications and Use Cases: Where these are applied, with real-world applications ranging from books to research papers to regulations


A working knowledge of Python, REST APIs, and the courage to ignore how dot product and clustering works

Speaker Info:

Anand is a co-founder of Gramener, a data science company. He leads a team that automates insights from data and narrates these as visual data stories. He is recognized as one of India's top 10 data scientists and is a regular PyCon speaker.

Anand is a gold medalist at IIM Bangalore and an alumnus of IIT Madras, London Business School, IBM, Infosys, Lehman Brothers, and BCG.

More importantly, he has hand-transcribed every Calvin & Hobbes strip ever and dreams of watching every film on the IMDb Top 250.

Speaker Links:

Section: Artificial Intelligence and Machine Learning
Type: Talk
Target Audience: Intermediate
Last Updated: